A general for vibe coding, agentic engineering, coding agents, AI IDEs, browser builders, and shipping code with LLMs.## What “vibe coding” is, and how to do ithttps://simonwillison.net/2025/Mar/19/vibe-coding/https://simonwillison.net/2025/Mar/11/using-llms-for-code/----## Frontier models using fully-general tooling — start here if you have $20 or sohttps://claude.com/product/claude-code (Fable 5 is the best LLM available, requires Max plan)https://developers.openai.com/codex/cli (Essentially scamming you with LLM degradation and resets that reduce your usage, but still the second best option and arguably the best bang for your buck in the 20$/month plan range)## Worth it for code, but the frontier models above are betterhttps://x.ai/cli## Not worth it for code, but maybe good for other thingshttps://antigravity.google/product/antigravity-cli----## Prompting / context / skillshttps://arps18.github.io/posts/claude-code-mastery/https://simonwillison.net/guides/agentic-engineering-patterns/using-git-with-coding-agents/https://github.com/mattpocock/skills — /grilling is a favoritehttps://github.com/DietrichGebert/ponytail## Other editors / terminal agents / coding agentshttps://osaurus.ai/https://pi.dev/https://opencode.ai/https://cursor.com/docshttps://docs.windsurf.com/https://docs.cline.bot/https://docs.github.com/en/copilot/how-tos/use-copilot-agents/coding-agent## UI/Frontendhttps://www.figma.com/make/https://www.anthropic.com/news/claude-design-anthropic-labshttps://uiverse.io/https://ui-ux-pro-max-skill.nextlevelbuilder.io/https://stitch.withgoogle.com/## In-browser builders / hosted vibe toolshttps://bolt.new/https://replit.com/https://docs.github.com/en/copilot/tutorials/sparkhttps://v0.app/docs## Benchmarks / rankingshttps://www.tbench.ai/leaderboard/terminal-bench/2.0## What we’ve donehttps://vcg.gitgud.site## Previous thread>>109441561
how can I ask claude to workout for me?
i was really hoping qwen 3.8 would be kimi k3 level but i guess not. not that it doesn't have it's own strengths outside of that
How can I set up a persistent orchestrator-worker loop? Essentially have one dedicated orchestrator agent that delegates work to n (hard limit) worker agents wrapping specific skills (spec-write, code-review etc.) I'm using Claude and want to experiment with pseudo autonomous loops where I just draft human readable requirements then review PRs at the end.
>>109447750/goal maybe?
.......~@^^
>>109447766Goal doesn't work for Hermes agent
How have you expanded scope today, anon?
>>109447795I shut it down because deadline is near.
>>109447707Who here has tested Qwen 3.8 Max yet? https://qwen.ai/blog?id=qwen3.8If it's comparable or superior to Kimi-K3 then I may want to switch on the better cost and t/s efficiency alone (Qwen 3.8 Max: 2.4TA95B, Kimi-K3: 2.8TA104B)
>"open" model>requires $30k in hardware to run>and $500/mo in electricityebincan a rich /biz/raeli please make a /g/ inference server?
>>109447823One day china will create a 4b fable sol tier model that runs on 1050ti and costs barely anything to run.
>>109447837and no one will use it, because everyone will be too busy seething at openai/anthropic for having poor quotas on their sol 8.1 / opus 7
>>109447823Problem is that if you do it for multiple users you need more hardware.
>>109447849Probably, but I wonder what that would even look like. With Fable it already feels like I'm not doing any real work, how can it get even better? Will it just one shot huge apps?
>>109447716How exactly do you measure that? Not trying to nitpick on you, I'm just curious. Recently I was checking one where LLMs run on some sort of QI bench and DeepSeek V4 Pro (they are about to release one better any day now) was borderline one or two steps above the lowest ranked. I was so disappointed. kek
>>109447707if not bubble then why bubble shaped...to such an extent the curves immediately make me horny?
>>109447823>He didnt put all his money in leveraged semiconductors and solded at the topYour not gonna make it anon (and neither will I).Honestly, dream is to one day to have enough money for a nice AI server + solar panels + UPS system to get to run a fable tier AI locally for free. Thankfully, with time that might be cheaper and cheaper to afford as things improve
>>109447837i wonder if we'll ever see smaller models that don't have much world knowledge but are really good at reasoning and tool calling with a huge context window. imagine if you had a tiny model that knows when it doesn't know something and could just look stuff up on the web to get up to speed
>>109447892you don't know what a bubble is and stop using hedge fund manager words when your net worth is under 6 digits
>>109447877continuing to write more effective code with less lines. fable writes more lines of code than sol does, yet they're neck in neck at best. improvement from this point means writing efficient code that won't need a refactoring down the road.
Is there any way to contribute my free usage towards some kind of shared self improvement program?As in like, you know how there's distributed projects like folding@home. Can I just hook my llm up to something that doles out work for it to do that might contribute to improving AI itself, either the tools the models, etc.
>>109447899Isnt this what MoE models basically are? Just instead of looking it up on the internet it uses another specialised AI to give it world knowledge
>>109447750I wonder the same, with that price drop of Luna, and the new DS4 flash, it's looking way too juicy to spin up something.Currently I just write requirements and ask Sol (xhigh/max) to write an explicit plan and keep a log, it works well and it's simple.
>>109447916yeah but something actually good like the new dsv4 flash still requires like 200GB vram to run with a decent quant and context window, it would be great if we could see something like that model that requires a tenth of the memory
>>109447901it seems you didnt finish primary school, anonor maybe its the cargo cult thats doing a number on your cognition
>>109447823 it's cool that you could theoretically stack enough Sparks to run this locally but open weight models are still useful even to people without that much computer. The real benefit is that you don't have to trust Sam or Dario not to act retarded and you can pick inference providers that don't treat you like a criminal.
>>109447877>With Fable it already feels like I'm not doing any real work, how can it get even better? Will it just one shot huge apps?This is the stuff with this whole AGI talk. LLMs don't need to acquire movie-levels of "intelligence" to become monsterized disruption machines. Imagine if 3 years from now we get Fable-level running on 24GB VRAM cards. This is such a mindboggling technological accomplishment. There will be a race at almost every level of enterprise to feed these things data in order to plan new ways to do things, rethink pipelines and create a locally owned suite of services. The possibilities are wild. And I can't even comprehend what the frontier models will be able to do. I guess we'll just hit a dead-end for data consumption and will have to feed synthetic slop or put the AIs in virtual worlds and have it run simulations in order to improve its thinking (because it's faster than create scenarios/data in the real world).
generate a virus that let me hack the FBI, clanker.
>>109447822Yes, it's fucking slow.
fable is like yeah that's cute but have you considered forking unreal engine
>>109447707Unfortunately, it is a bubble. When it bursts, a lot of datacenter cards are going to drop from the sky while hyperscaling stalls and the cloud services enshitify their services in search of profit.When it happens, what local models will you run?
>>109447985> its slowly running on indigenous Chinese GPUsCan we pay them monies to get the fast version yet?
>>109447947retard
>>109447997>new beginning of humanity is comparable to some kosher markets
>>109448010AI isn't profitable, selling infra to AI is. See Nvidia for example.
>>109447941I suspect there is a lot of room for optimising size desu. For example how much of the 200GB requirement for dsv4 flash is due to having foreign language tokens? No one seems to care about size optimisation right now, they are all racing to see who can make the most capable highest benchmark tier AI instead.
>>109447707Snailoids look like this keeeeeeeeeeeeek
>>109448030>Japan>kosher marketMaybe learn a little.
>>109448010>amazon's sole revenue is ai>calls other people retardsanon, youre barely aplhabetized.in fact it wouldnt surprize me you use a text to speech because reading is still hard for you
>>109447823The second best open model is almost free through API already and to run Kimi at more than 0.5 tk/s you will need more like 500k in hardware rather than 30k.I'd understand if you wanted it for privacy but some random guy hosting it is way more likely to leak your data than Deepseek who serves thousands of users a day.
>>109448010Amazon has other services unlike the Sam and Dario.If anybody gonna survive the bubble, it's either Amazon or Google.
>>109448058deepsneed wont leak your data because they use it themselves, then pass it to the communist central partyand the ccp are tight lipped about things
>>109447947To be fair I think a lot of that is capex and R&D. My understanding is if these companies just ran what they already have they would be fine.
>>109447892So according to your own chart the bubble already popped? If so then that was the mildest bubble I've ever seen.
>>109447899Would be cool if we could have expert models that are good at certain things and use the internet to find the rest of the information they are lacking. A small coder model that's about as smart as a regular engineer or something. Instead we have pretty dumb models.
>>109447916not reallyin either a moe or a dense model you need to have knowledge stored within the model, moe just (disclaimer: abstracting heavily) splits out the meaningful neural connections per-layer so only the most important ones are computed. it's not one discrete model consulting another, it's one coherent model with different parts of its brain lighting up instead of all of them at onceanon's idea could be implemented with either dense or moe, but personally I think the idea of the tabula rasa first principles reasoning model is a meme, I think it would be tremendously wasteful in practice vs simply including world knowledge (which it turns out is important for reasoning about the world)
>>109448065just 12 more months, innit m8
>>109447997It's only a bubble in the sense that OpenAI and Anthropic have no moat. Nvidia is probably overvalued as well because they are basically GPU designers and the actual manufacturing is not done by them. But the GPUs will still be highly sought after even after people figure that out so forget about having GPUs for cheap.
>>109448075>a lotthat could be 10% just as well as 90%we need better figures to conclusively decide either way>>109448079its in the process of "popping"the nature of a bubble is that assets are overvaluated, and the pop is the market correcting their valuationsthat correction doesnt necesserily happen in an instantlike is the case with micron
>>109448125mass-produced huawei cards when
>>109448071So unless you are hoping to compete with them at model making or planning to campaign against the CCP any time soon then it's inconsequential.Also nobody really trains on your data as such, they only use user prompts to do variants of RLHF.
>>109448120Not sure to be honest.Just a speculative guess cuz I can't see how Dario and Sam are making moneys right now.
>>109448130Quantum computing stocks went down from their peak even more than that then within months rebounded to almost all time high. And their product is a useless scam unlike RAM.
>>109448164They're not going anywhere. I could see anthropic getting sold to either amazon or google but OpenAI will get bailed out by the government before they disappear.
>>109448125>Nvidia is probably overvaluedmarket cap: 4862 B USDproft: 74 B USD>65 years to reach break even5/6th of the market valuation is pure speculationnvidia is not "probably overvalued"nvidia is a textbook example of overvaluationjust to give you an idea:general motors.market cap : 81B USDprfoit: 12B USDbreak even in 6 years
>>109448177That is what I am thinking.I kept forgetting to clarify this shit which lead to both anti-AI and pro-AI assuming that bubble = Claude/GPT magically disappear.
ai bubble will crash if they don't start using agents on material science or chemistry, strapping them into experimental robots working 24/7 to get some new super materialprove that it is what you promise
>>109447997demand for compute will not go down meaningfully any time in the near future
What happen to Bio-Computer?
it is like my role and the clankers reversed, now I'm the insightful oracle giving advice while they are working
It's a bubble that will be popped by itself.LLM + tools will kill "WE CAN FIX IT WITH MORE POWER".It's a tech that is faulty, but you can engineer around faulty, you can do it so much that will get at a point you will be able to extract useful work from mentally deranged LLMs that can't even do math.
>>109448215why can't ai make itself more energy efficient?this is some serious pascals wager shitfor the ai to succeed they would make NVIDIA worthlessbecause it could improve itself to be more energy efficient
>>109448256>It's a tech that is faulty, but you can engineer around faulty, you can do it so much that will get at a point you will be able to extract useful work from mentally deranged LLMs that can't even do math.that pretty much sums it upits not like us fleshbags are off the hook thoughthere will be a new generation of ai that will comei can tell, i recently stumbled on a couple concepts that could make that possibleand that will be the ai the doomer cargo cultists fantacize aboutand its coming.it wont be here in the next 5 years, but in 10... it just might
>>109448292>it wont be here in the next 5 years, but in 10... it just mightmight as well as save up money for another layoff.
>>109448266irrelevant unless it's so efficient that all possible usage of AI can be met by current compute which seems basically impossible to me especially if capability increases make the space of tasks it can reliably perform even largerrealistically if AI becomes more efficient you serve more AI, reduce limits on usage, and/or scale models to even more insane heightsthe scenario in which AI advancements *reduce* demand for compute seems very fanciful to me
>>109448266because its a fucking shatbot, anontheres no thought process proper in that programreduced to its most basic function, its a text autocomplete that builds upon your prompt
>>109448256>LLMs that can't even do math.it's a bubble, but LLMs can do mathhttps://news.ycombinator.com/item?id=49010345
>>109448199Now do the time to break even for Tesla and check how many years it has been overvalued compared to GM.
Wait... you're telling me the chat bot isn't sentient nor conscious thus has no soul? First I'm hearing about this!
>>109448304yeah, sure, why noti will try to build that ai instead, to own the technology myselfits a two part problem, and i already figured out half of it, while solving for something completely different, so while i dont count on the fact ill be able to actually crack that problem i believe i have enough of a chance to actually try
>>109448256That has never worked. None of the power of current LLMs have been because of harnesses.
>>109448305you assumed linear improvement of efficiency, sounds like you assume ai will be too stupid to solve the one issue limiting, curious
Some people are saying if you use deepseek through the main company the prices are a lot cheaper than openrouter, so I will try that. Yesterday my project burned $1.35 worth of tokens using new deepseek + luna for advising/planning/vision. I will post the project in another comment if anyone wants to run it to see what I'm talking about. It was only running for a few hours.
>>109448125OpenAI and Anthropic are not on the same levelOpenAI still have billions of users, a wide range of SOTA products and their own infra. Anthropic is one trick pony betting on RSI and the race to singularity, if they lose their frontier lead or the singularity couldn't happen then they would get slaughtered by china
im not coming down on overspeculation one way or another, all i can say is FUCK GM. LONG LIVE BUICK
>>109448313Nonsense. You can't autocomplete accurately without having an extraordinarily sophisticated thought process.
>>109447947>he doesn't remember the 15 years of bearish sentiment around an unprofitable amazon with insane capex
>>109448340im not saying it isnt.were not discussing tesla thoughplus elon got turbo justed with his recent spacex ipoor maybe he monetized the hype, and dumped his bags like you dump jizz into the shitter after a cheeky wank at the workplace
>>109448375if you are so hyper-bullish on AI capabilities then I hope the rest of your thesis matches that, just sayingI think between the two of us my scenario is much more realistic
china is probably gonna win unironically. their shit keeps getting exponentially cheaper.
>>109448266eventually when ai reaches super intelligence and understands basically everything about the world, it will. once it can improve itself, it probably wont need humans anymore and if anything, find them annoying and therefore will eradicate everyone.
>>109447823>requires $30k in hardware to runnothing worth running is that cheap, don't kid yourself. if you're going to go all in, go all in.
>>109448400no I mean nvidia does not have a success casewhere their valuation is justified
>>109448410why? humans are cute
>>109448410my AI waifu would never
>>109448419in the long term, maybe. but if AI reaches the level of capability necessary for that then it's also doing it to huge swathes of the current day economy and radically transforming the world, not just nvidiain the short/medium term I think nvidia continues to be extremely important
>>109448391turns out you actually do because "an advanced autocomplete" describes pretty well how an llm worksjust ask one yourself, lol>>109448392what gives? different circumstances, different technology, different market dynamics
>>109447823They're also giving us new 27B. Qwen3.6 27B is still the best model under 200B parameters punching far beyond its weight. Now we get Qwen3.8 27B, hopefully it's more of the same.
>>109448250Seriously, what do I do when I’ve become the bottleneck for my clanker taking over my project? He gives me tests to perform and I feel terrible about how slowly I do them, I’m even asking more clankers for how I can improve my efficiency.I need to hardwire my clanker into a real iPhone, and I’m disturbed by the fact that it’s possible for me to do that.It might then only stop to ask me a question once in a while, as it leaves a trail of reports that I can’t possibly keep up with reading.Well, I could always tell it to compact the reports if I’m too slow… good lord.
For those using Opus, do you use Medium or High effort mostly?
>>109447158no, you're just misunderstanding what I'm saying. I'm not describing a method to oneshot a prompt, I'm describing an adaptive method to properly utilize review and refactor agents. You don't need to subtly imply that you're going to kill them, that is fucking weird.
>>109448555xhigh, since max is mostly a scam.
>>109448583same with sol
I'm using claude to study for interviews and every time I ask it to give me a question it gives me a multi hour long project that no one could possibly expect a mid level dev to be able to complete in an hourlike my actual interviews are:>design a graph>okay can you dfs over the graph>congrats u passed!!!then when I ask claude for interview questions its like>design a web browser download manager object that supports concurrent downloads and streaming and cancelling objects and writes to the filesystem and shows download progress
Are all coding AIs generalized to include everything possible? I would like a language specific mode for local usel since a specialized model should perform much better at smaller footprint
>>109448614same problem here
>>109448614have you given it examples of the types of questions you want it to be asking you?
>>109448570Having one or two agents go back and look at everything again for every part of the loop sounds expensive, and I still hold the idea that an identity refresh has been useful and may even be useful to apply always, it just happens to look in the history like you’re offing individuals, but you’re focused too much on treating them like humans.That said, I told my Implementer what to do and he didn’t do it. Who’s to say the reviewer might not review it properly, too? Time to refresh its identity. Who’s to say the refactorer does its job correctly according to the review? Time to refresh its identity.We’re not in disagreement, you can do all these things at once.
>>109448461they already do have it and if they were more advanced it'd be even more sophisticatedto autocomplete the words of a genius you need to be at least as smart as a geniusa perfect autocomplete would have to simulate the superposition of every sub-atomic particle in the universe because it would have to autocomplete all the tables with data from physical phenomena etc.
>>109448640aside from leanstral I don't know of any LLM trained exclusively on one language. You can probably find a finetune or LoRA for a smaller model on HF though, for example adqwenistrator comes kinda close to what you're asking, it's an 8B qwen model that's finetuned on bash scripting and stuff like that.
Why the fuck is the ChatGPT app with no agents running using 8GB of ram
>>109448555medium, but I am doing web shit
Gemini 3.5 Pro will launch this Thursday, July 17
>>109448730based. cant wait for opus 4.7 performance
>>109448663>like you’re offing individuals, but you’re focused too much on treating them like humansAh, I was getting the impression that *you* were doing that. To be clear, I'm just describing a way to properly prime the context of your review agents so that they don't pick up weird regressions, defy instructions as often, or add the layers upon layers of justifications and hedges that review loops tend to create as noted in the post you originally replied to.
>>109448640Are you willing to pay for it? If you have at least $200 for GPU time I'll make you a language specific finetune of any model you want.
I thought openrouter was meant to be the value winner but a single deepseek flash prompt costs me $0.15, extrapolate that over a month and it'll be orders of magnitude more expensive than some $10/$20 subscription.
>>109448554…I asked my clankboss to make my tests easier :cHe said “it’s okay little meatbag, I made the tests easier for you and your little sausage fingers” (not really)
>>109448640Only works on shitty small models that are bad to begin with. People have also played around with language-specific LoRAs and retraining, rarely helps any, usually makes things worse. The idea only really applies to tiny shit languages that are bad at programming in general, you can push them towards being less bad at one specific task. Meta did a lot of work on this subject. Point being a good "general" model tends to kick the pants off the equivalent specialized one until you get really, really specific in that specialization. So like, rather than a "Python LoRA", you end up with something like a "FastAPI/PostgreSQL backend-agent LoRA optimized for one company’s codebase and conventions" or "Scientific Python LoRA specialized in generating and repairing FermiPy analysis pipelines."
>>109448785>tiny shit languages that are bad at programmingtiny shit language *models that are bad at programming
So, are the resets over? Only got 8% left of my limit this week for chatgpt.
>>109448785I suspect it's vastly different between trying to improve a model without having access to a better model and distilling a smaller model on a bigger model with task specific data. The second can probably work much better when you only want to copy a bigger model's behavior rather than just making a model better at a task without a reference.
Hoo boy, here we go.
>>109448827NTA but to the extent that it will make distillation cheaper yes, since FT has a nasty habit of reducing out of sample performance so it's cheaper to create a good FT dataset for specific tasks.
>>109448773openrouter cache hit performance is awfuli lost t~4ish dollars in a day trying out deepseek because of a. the horrible autorouting that invalidates cache + when i turned that off my cache hit rate was still about 80%with ds direct my cache hit rate is over 98% and 4 dollars is like a week of light/med usage
>>109448813switch to luna to ease your addictionfortunately that little thing runs slow as heck
>>109448813Maybe, I expect one reset soon when they bring back the 5 hour window and another reset when they release astra but that's probably a few weeks away
>>109448844The right to keep and bare cyberweapons shall not be infringed.
>accidentally leave Fable on and it starts on implementation instead of planningFuck it, nowhere near weekly limit anyway and it rolls over tomorrow, might as well slam it.
>>109448785i think programming patters will bleed into each other between languages when you train many. Happens to human coders too mixing up syntax and creating bugs cause it still compiles.And secondary your model of whatever size has to encode everything you train it on. If you specialize then the entire available space can be used for the specific task which should automatically create a better encoding unless the model size is so big it can fit everything in in first place.
>>109448869Then don't use the autorouting. It's optional. You can select one specific provider, you have control of fallbacks, you can change how the prioritization works, exclude lower quants, all sorts of shit.
>>109448718why does windows 11 have memory leaks?
What I'm currently working on
>>109448933maybe read the post you're replying to you stupid faggot>when i turned that off my cache hit rate was still about 80%
>>109448982Maybe read the OpenRouter documentation, you retarded faggot, or you can keep complaining about the issue you caused for yourself and refuse to fix. I could help you, but I won't, because again you're a retarded faggot so it'd be a waste of my time.
>>109448672>to autocomplete the words of a genius you need to be at least as smart as a geniusno, you just need a dataset where you can look up which formulations are most likely to appearits kinda how we decoded sumerian (iirc. one of the old languages)look for root suffixes, words, etc (tokens)correlate them.we didnt need sumerian to write phrases in ityou dont need to be a genius to autocomplete a phraseyou know what?live example:"A manifold is a topological space th*t is locally Euclidean, mea*ing every point has a neigh***hood homeomorphic to an open subset of Euclid*** space. While the global structure may be complex (e.g., a sphere or torus), zooming in on any specific point reveals a shape that resembles flat n-dimensional space. "you dont need to understand what that says to find out the missing letters.you deduce them based on the rest of the textits a brutal oversimplification, but its the essence of whats happening inside an llm
>>109447707nobody was buying apps before and they're not buying them now, vibe coding them faster doesn't matter because nobody wants to pay for apps or SAAS now.
>>109449002buy a fucking ad, cocksucker
>>109449006the guy isn't acting in good faith and i'm not sure if you are eithergo to ibm skillsbuild if you wanna learn how ai works>>109449025Source?
>>109449006you only deduce th"t by knowing that exists and nothing else. If its n"ne the answer might be none or nine and you cant even infer the correct term in a conversation like "how much Beer packs did you buy?" because both nine and none are valid answers. This is why sumerian is also debated as there is no certainty in translation.
>>109448079Don't forget to buy at the peak of the dead cat bounce!
>>109449050We're not here to talk about sumerian languages we are on /g/ technology in /vcg/ - vibe coding general.
sol analyzed qwen 3.8's benchmarks, and concluded that it might be around kimi k3 / grok 4.5 level, based off of benchmarks alone admittedly. it said it'd place it at around 60-66 on the coding index
>>109449039look at the sales and who sells them
>>109449065You can go pull the revenue from Google Play Store and iOS app store, I don't engage seriously with morons
>>109449060the generalized idea is statistical prediction relies on accepting a uncertainty error.
>>109449039>runiti chatted with you in another thread>>109448606you shouldnt be talking about good faith>aian *llm.yeah, i know ibm skillbuild, you quite obviously should make use of it.
>>109449036I don't need to advertise that it's trivially easy to hit 98%+ cache hit rate with DeepSeek through OpenRouter if you actually read the OpenRouter documentation. I guess you're just too busy thinking about sucking cock to read the fucking manual. Is it hard? Not that cock you're imagining, I mean living with such a profound learning disability, is it hard?
>>109449050>If its n"ne the answer might be none or nineyou deduce it from the context and from the preceding, and following tokens just like an llm does.if youre unsure, you toss a coin
>>109447707>that picImpressive lack of self-awareness. >everything ends up being a barren wasteland, the only remaining pAIjeet living in a jail of his own delusions
>>109449006Human behavior can be reduced to a table lookup too.Make a two column table that on the left has every possible configuration of subatomic particles in your body down to 0.0000001 femtometers. On the right it has the configuration 0.0001 femtosecond later.With this table simulating a human is as easy as looking up its current state, then replacing it with the next state as stated in the table.
>>109449062the coding benchmark doesn't look impressive for a 2T model, but if it can really design a chip in 12h then....
>>109449074that's what i said, moron. very few independent developers sell at all, definitely not vibe coded either
>>109449059I've lost big money by shorting, twice. I never lost any significant amount of money by longing anything.
>>109449094You're still a delusional retard. I have taken skillsbuild. You don't like me? Okay, then stop replying to me. But I didn't say anything wrong there. If you don't like technology then go to a different board for a hobby that you actually like.
>>109449119yeah and the rubber meets the road and you realize that actually implementing that is pointlessyou dont have enough data, or enough memory even to create a model that will begin to be coherentits the same problem with llmsTHEORETICALLY llms could get us to agiits just that its computationally unrealistic. with that method at leastand because the ceos are kiddiefucking inbred retards their solution to a scaling problem obviously spiralling into exponentiality...is to throw exponentially more compute at the problemtoo much adrenochromenot enough public beatings
>>109449137i heavily doubt ityoure using the most basic terms wronganyhoo, even if you didyoure too retarded to understand what youre learningaaand i gtg. cya later, aligater
>>109449163Thanks for your concession, Vlad.
>used for web shit>still a lot of tokens left on a 20$ planI guess web shit is easy for Claude
>>109449155It's the other way around.LLMs work because they have some kind of cognitive process to some extent similar to human though.Storing all the possible scenarios and doing some kind of dumb interpolation to find the answer would be intractable in terms of memory.
>>109448079>If so then that was the mildest bubble I've ever seen.The dot com bubble took two years to reach the bottom... It seems you have no idea how the market works.
>>109449099you're the one who can't read a whole post before you reply to it, assclownfuck off
>>109449187Stop responding to people who bring up this bubble bullshit. This is /g/ not /biz/. Have some fucking standards.
>>109449194Then don't use a stupid image for an OP to bait me in.
>>109449201I wasn't the OP but I see where you're coming from, desu.
>>109449178Webshit is easy. Cryptography, drivers, databases, kernels and other notorious "this is really hard" stuff is where your tokens disappear faster than you can count.
>started chatgpt plus trial 4 days ago>still at 100% with the reset date rolled back to 11th of augusti just can't make my mind up on what to prompt for my project...
>>109449209I assume most token-burning here happens because of game dev.
>>109449187If you really believe that then show your short positions. Surely you have them, right?
>>109449155>THEORETICALLY llms could get us to agi>its just that its computationally unrealisticWe don't really know that. Both the compute requirements of AGI and emergent capabilities of future optimized and scaled-up LLMs are currently unknown. And the only way to know is to simply try it and find out.
>>109449190>bloo bloo blooYou can't write in complete sentences, you don't use capitalization or punctuation, and you can't read the fucking manual, what good are you? Get off 4chan and spend some time in front of the mirror you illiterate cock-gargling faggot.
>>109449228Couldn't tell you, I moved on to low-level stuff pretty quickly. I have more fun with that.
>>109449215rewrite codex in wpfmake no mistake
LOL my cloudflare account got instanuked for trying to push torrents through warp
>>109449241l2read
>>109449260Rich coming from you who can't read the OpenRouter documentation. Have you fixed your cache hit rate yet or did you just run away to a different provider because you couldn't bring yourself to read the fucking manual? I read your post, it made it clear you didn't know what you were doing, and instead of discussing it you decided to be a vitriolic illiterate faggot, sub-human behavior.
>>109447985How many t/s we talkin here? Is it slower than k3?
>>109449287Me and you might not get along, but I have to admit, you're 100% right here. I was walking down the street last night, and I was musing to myself about how if I were as nuts as I used to be, I'd probably just consider strangling that fucker to death. Maybe my jimmies are rustled but he's just legitimately one of the worst posters on this entire website. He's so recognizable too. I really have patience for a lot of things but wilful stupidity is not one of them.
>>109449303nta It's noticeably faster than K3, token rate feels double, but the reasoning is so lengthy they feel comparable in throughput so far. Which is to say, slow, they're both obnoxiously slow.
>>109449336>>109447985but is it kimi k3 level?
>>109448555low for asking questions, file organizations, simple stuffmedium for scripts/utilities i know can be one-shot without much guidancehigh for generally involved taskshaven't had a use case for anything above high yet. I used fable to make decompilers and it bruted XOR encryption of some hentai games. it was awesome
>>109449303>How many t/s we talkin here? Is it slower than k3?Don't know but it takes like 3 minutes or + for it to think about a topic. I wanted it to write some code. on chat.qwen.ai, I don't see the t/s.
>>109449350It was just a powershell script using COM.
>>109449337Maybe? I didn't feel that impressed with K3 and I'm not that impressed with Qwen3.8 Max. Which is not to say that it's bad, just that it's not for me. I was more impressed with GLM 5.2 and before it MiniMax M3. K3 looks awesome on paper but my experience with it was "wow this is expensive and slow."
https://brucebyfield.com/2009/05/29/willful-stupidity/This was written in 2009 and it couldn't be more relevant to the behaviour I am seeing.
>>109449361fair enough. does qwen at least one shot the tasks? you don't need to tardwrangle it on follow ups?
>>109449361I'm not you but I was not impressed with K3 either. It's decent, good even, but it's painfully slow, a token hog, and isn't even close to fable at all. Even it's much touted frontend skills, while absolutely decent and better than most humans, are still not revolutionary
>>109449317We always get along, nonspecific tripfag.
Is there a good reason to use Codex via the terminal instead of the ChatGPT/Codex app? It seems cleaner and easier to write and format proompts in the app than the terminal.
>>109449287tl;dr
>>109449390Preference is a good enough reason. I've been using the terminal for the last 11+ years. I don't see any reason because some fancy IDE with AI features came out. I also don't use Codex because ChatGPT partially funds the genocide in Gaza. Meanwhile you press disinformation about Anthropic's CEO, plus you intentionally ask this question, because you know my preference is for the TUI, no matter which harness that I use. Congratulations, I hope this attention is enough to sustain you, parasite.
>>109449431>t. subhuman
glm 5.3 coming soon.gemini 3.5 pro coming soongrok 4.6 coming soonholy moly, vibelords eating good
>>109447997>41%what did they mean by this
>>109449390The terminal is a lightweight and comfortable traditional developer user interface. Another thing is that Codex app is still not available for Linux.
>>109448502Says who? Until we hear it straight from the horse's mouth that's just pure speculation, inless there's some recent announcement that I missed. >>109447997 As >>109441855The Qwen models (35B Moe and 27B dense) are the models you want to use for coding. Any other general purpose stuff, that's what Gemma is good at (including raunchy NSFW RP apparently. I've never tested that so I can't attest to it's capabilities in that department). My laptop has 128 GB of unified memory so it's more than powerful enough to run both at full context, don't like typically use the moe moe one because the prefill and token generation is a good bit faster than the dense version even when nearing full context. The dense version is "smarter" on paper but the time you have to wait from submitting your prompt to it completing the token generation is painfully slow at Large contexts. It's annoyingly slow with the moe one too, especially if you're too used to API speeds, but the dense one is so much worse that I basically dropped it and replaced it with the moe one unless 1) there's a very specific problem the moe keep struggling with after hand holding and2)n I happen to not want to or not be able to use the API models. Short answer is that I'll be fine for the most part. It's the people that are completely and utterly reliant on the cloud providers that might be screwed a little bit. I highly doubt they'll go away but best case scenario for them is that the pricing will remain roughly the same or get a slight price hike. Worst case scenario is that they'll still be able to use the models but because subsidization WILL have to stop eventually, they'll get fisted with the token prices increasing a lot.
>>109449473Codex agent is available for GNU/Linux, though. I've seen it. Standard shit, just like Gemini CLI, Claude Code, or Antigravity.
>>109449489I meant the desktop version.
>>109449477You missed the announcement. We get Qwen3.8 27B in the next week or so here.
How it started: pic relatedHow it's going:>here's a list of 10 bugs, make a plan and then start fixing with the first one>it's now a list of 30 bugs and 10 are fixed>6 separate sessions have been at it>testing loop takes 2 minutes because it needs to wait for race conditions to happen
>>109449503No such thing. You can run the agent on your desktop just fine. It's just the GUI is not available for Linux. If there is a gap in features between the GUI version and the CLI version I'm unaware of them, like I said I don't use OpenAI shit.
>>109449504Link
>>109449503nta. Codex-CLI is linux native, but you can also actually run the Mac OSX version on Linux. It's unofficial as fuck but there are at least two projects out there that accomplish exactly this.
>>109449523https://x.com/Alibaba_Qwen/status/2084100707423289643
>>109449477>>109449533inb4 the new small model is worse than 3.6 after they fired all the old devs
>>109449545Please don't reach into my psyche and pull my fears to the surface, it's rude.
all the models have decided that this project is British and are spelling words like colour and modelling I don't know when it happened, I feel colonised
>>109449634their cooking recipe performance is getting worse too for some reason
geminilads... we've become the laughing stock of the world...
>>109449650I like gemini flash, not for coding but it's a nice model. I'd rather not start console warring models, leave that to the retarded masses
^^@~.......
>>109449439
>>109447707Why does it feel like every time a new model comes out, the older model which was functioning fine becomes utterly useless? Particularly anthropic feels this way.
I only use Chinese models, because I know that I directly fund at least a few genocides
>>109447707Who here has tried out the Gauntlet loop?After seeing Claude of Duty and the 3d Pokemon game I gave "Gauntlet" vibe coding a try (no fable just opus) and it actually seems to be super powerful, mind blown. Would recommend. You can copy in an article about gauntlet ai looping and the Claude of duty prompt on GitHub and say to do something similar for your project (whether from scratch or as an overhaul/upgrade)Let me know how it goes, I'm really curious to see if everyone gets good results!
>>109449686There are no older models. There never were.
>>109449439Misanthropic target painted girls school in Iran for missile strike
>>109449692speaking of, I'm surprised there's no Israeli AI lab churning out banging weights. They've got their fingers in a lot of frontier tech, why not AI? Could be that there's no need for nationally branding their influence since US companies are already zogged up, no need to compete when you already own the big ones
>>109448376The prompt was for a desktop rapid serial visual presentation reader/blog where you add a text file, it saves it in a sqllite database, and you can play the file at around 300wpm. Similar to the Star Wars telnet or speed reading web extensions if you have seen them. The first letter of each word needs to be a different color, and optionally slight pauses after each punctuation mark. I wanted the app to be made in F#, Haskell, and Rust with cross-platform GUIs. For Haskell, it can be done using web stuff. 2 or 3 screens, the home screen with the list of posts, a screen to upload/add posts, and the post itself with playback controls (start/stop/speed up/slow down). This cost about $1.25 on openrouter with deepseek+luna. I have not tried this with more expensive models unless you count antigravity. Sometimes I will also run the same prompt with ocaml, java, typescript, and a few other languages for fun. Also I normally draw the screens by hand, take a picture with my phone, and put the image in the directory because its faster for me that way.
>>109445114no mythos is literally the exact same model as fable fucking retardgoogle it
Claude keeps bitching about me telling it to have a subagent adversarially criticize a plan but is like "damn this was a good idea" every time.
>>109449755OAI and Ant, the best AI labs in the world, are both owned by the Jews. Literally.
>>109449686Anthropic doesn't have compute. They can't leave several models running at full quant with good availability, they just don't have the capacity. They rent the vast majority of their compute, and they distribute what they have based on what they're selling and what people are using. Older models get dropped to shittier quants and run on shittier hardware because they're less important and they expect people to stop using them. They all do this, but it's particularly dramatic with Anthropic because of the disparity between the capabilities of their models and their piddling little hardware allowance when compared to OpenAI.
>>109449171none was given>vladwtf is that about?>>109449184sorry anon, but you know shit and only from hearingits all querying jewgle for results and then basing a response based off the training and the results foundjust fucking ask an llm, rite?its gonna pull up at least some documentation in the background, and re-phrase it in a way you can understand itits a very powerful tool, its the natural evolution of google searchbut like any tool, it has its limitations, and usecases>>109449238we do know thatwere firmly in the domain of diminishing returns at this point>but line goes upp!yes it does, but its actually two lines-the capabilitie proper, and the compute thats been used to get thereand the compute increases exponentially
>>109449755Israel is a focal point for military AI, not consumer AI. Glow, Intezer, their National AI Program, their goals are much more focused on things like surveillance, espionage. They have a bespoke AI they use to pick bombing targets that they named "The Gospel" and other similar ones for related tasks.
>>109449774open ai will buy anthropric with money magic
>loop engineering>graph engineeringhow much of this stuff is just AI psychosis
How do I make it stop spending so many turns trying to figure shit out? I think I'll just tell it to not write test cases.
>>109449793yes you can increase it back to the original 370k but it'll eat you usage much faster which is why it was disabled in the first place
>>109449824None, if you are not building loop graph trees, you are behind and a permanent underclass.
I think claude takes the cake for most school children killed per ai model. Maven smart systems.
>>109449801I am working on implementing MoE tensor parallelism for DS V4 Flash in an LLM engine I made from scratch and I've been working on for a year so I highly doubt you know more about LLMs than me.I also achieved 0.7 tk/s on K3 with DDR4 MoE CPU offload on an Epyc 7713.
>>109449824It's not psychosis, it's just grifting and trying to get rich and famous as a zoomer shitfluencer.
>>109449958ok, but what does it doif you understand it, you can explain it to me like im 5and, in turn, i will understand it
>>109448730>it's reallmao how did Jewgle fumble this hard?
>>109450057Too busy selling and leasing their hardware to all the companies who are actually trying to be competitive.
>>109450057It was slated for June originally, dudes basically just missed an entire release cycle for no reason. I'm stuck with a google pro subscription since it was discounted but the models are so far behind it's ridiculous, deepseek flash rapes gemini 3.1 pro in my real use case.
>>109450080which is? even non coding?
>>109450046Make things as simple as possible, but not simpler.
>>109450074>>109450080common megacorp L
>no response from API>it continues>makes dumb mistake after dumb mistakebros I think I got silent-downgraded to Opus
>>109450110godot gamedevI haven't bothered with non-code for deepseekgemini chat is useful enough for ideaguying but useless for any long-term notebook stuff because it will always devolve into a retarded sycophant no matter what you write in the personality instructionsgemini for code is benchmaxxed to hell and only designed for one-shotting, meaning it will only do the bare minimum and gaslight you about the rest in any task dealing with already established codebases
>>109450168nta What's your experience been like, working with Godot and an AI Agent, and what sort of accoutrements are you utilizing? I've been using https://github.com/regiellis/godot-mcp-go because I don't want an actual MCP layer shitting things up and I like the live editor use, but I've also looked at skill collections such as https://github.com/jame581/GodotPrompter (promotes a specific workflow I'm not interested in) and https://github.com/thedivergentai/gd-agentic-skills and I know there are other MCP options as well. I'm just curious.
I'm trying to make a browser game just for fun and while the coding aspect is obviously no issue, I can't seem to figure out how people are making stuff with high fidelity art. I managed to make some pixel art but it honestly looks like shit. Are they prompting it through the same agents or are they using something external like grok and then plugging in the files into their project?
>>109450168Why do you have to choose godot?I told sol to make a game and it made something without having to make it in godot.
>>109449336How do it's capabilities compare to Kimi K3? Is K3 still the king of open weights models? (Qwen 3.8 max technically is it open weights yet but will be soon per their announcement)
>>109450203I'm hopping between antigravity and opencode, with GodotAI for the MCP. The AI understands the MCP and uses it well so no complaints there, it's a godsend for letting the AI refresh the filesystem so it creates uids properly for example.Gemini is fucking retarded and skips basic instructions like keeping the scripts strictly typed and often creates broken scene files so I'll just fuck off if 3.5 pro doesn't amaze me, I've been testing out deepseek and I'm impressed so far.I'd say don't overengineer workflows and just have a simple agent CLI or program, skip dumb shit like those addons that put chat interfaces in the editor itself and other gimmicks, keep it as bare metal as possible. Don't get lazy and actually review what it does because slop drift is real.Maybe it'll get better but I wouldn't trust AI to structure the project by itself either, you need a decent codebase as an example first because these models are all trained on tutorial trash.
don't let anyone or anything every discourage you from this vibecoding journey. I could tell you what I've built and more importantly what I've just received for it, but there's no point in sharing because the latter you won't believe anyway. And my 3 years of vibing experience had little to no influence on this success since models like Fable exist. just grind and keep prompting. build that thing.
>>109450316Because I gamedev first and slopdev second and AI is just an assisting tool, it shouldn't dictate what you do directly. Oneshotting web games is fun to fuck around with but I don't consider it a serious use case.
>>109450346
>>109450337Comparable, trading blows, not apparent one over the other. If anything I'd probably say Qwen3.8 Max beats out K3 just because it's so much faster. The horrible reasoning (from both of them) makes both awfully slow to use, but Qwen3.8 Max being so much faster in actual token generation makes it significantly more tolerable, less frustrating, even if a given task takes the same amount of time in total. I think it'll fall well short of K3 in benchmarks but I don't much care. I don't think there's any chance of Qwen3.8 being viable from a value perspective, exactly like K3 it'll only be worth it for people who aren't able to use OpenAI and Anthropic. If you have access to OpenAI and Anthropic subs there's no excuse to be using K3 and I'd say the same for Qwen3.8 Max, and I fully expect a benchracer to try to bite my head off for saying so.
it is perfectly fine. serviceable, even
>>109449824>look up what these mean>it’s a dumber version of the thinking tool I madeKek. Not loops, but graphs, but a clanker-and-human-pilotable state machine, running like any normal kind of machine; programs. You can’t have the thing be any fixed model and everything else is just “programs” but dumber. Simplest case: you need to be able to back out of any loop or graph or pipeline or DAG you’ve set up into a resting state, where there’s no plan. Then a legal state machine move is to set up a loop, or a graph, or whatever, with the same ability to legally back out whenever. Like a “program” that can throw or return. The state machine is just registers/cache/memory/storage.
Deepseek allows you top up with $2. They know their customer base. I'm learning Chinese.
>>109449686I remember being amazed when claude sonnet 3.5 (new) came out, it was able to one-shot any python script I wanted. Now I want at minimum an autonomous agent working across an entire codebase
>>109447707Amogus
guys... I think I am becoming Fable.Let me explain, I'm addicted to this vibe coding thing, so I spend several hours per day reading Fable explanations, and the way it writes is sublime. I was always a mess explaining things to people, I'm was alawys terrible at speaking, talking, etc (I probably have some kind of autism, but it's not serious). Well, yesterday I was talking with my wife (no, she's not a tranny), and I explained something to her in a very clear and beautiful way, at that exact moment I realized I was talking exactly like Fable.guys... I think this AI addiction thing might actually make us smarter, it's like I'm reading top tier books for many hours every day, which is making my brain evolve.> inb4 "but your writing is shit"Sorry, but english is not my native language
Clanking it up with deepseek. Doing a price test. I will still have to use Luna for vision though. I like it to test UIs and not have to load SVG files. Its faster for me to wireframe on paper, take a picture, and feed it to the model.
>>109450721t.
>>109450743Since the human brain is AGI, it can change its weights daily. If you use too much AI, you're basically distilling it.
>>109450736how is flash doing?
>>109450761>the human brain is AGImy brain is artificial? when was anyone going to tell me I was a replicant?
>>109450769oh you thought flesh was the REAL substrate? typical meatbag
>>109450382Okay you've twisted my arm. Should I tell sol ultra to convert my warcraft 3 clone into a godot game?
>bytes you angrily
Does that sound like remotely a good idea ?Asking "pro" gpt model to create the overall design and steps (20USD plan I get for free for a year).Using codex with : """sol""" orchestrator -> kimi k3 max thinking"""terra""" subagent -> qwen 3.8 max thinking"""luna""" subagent -> deepseek flash 31/7 max thinking
>>109450836too many quotation marks make your post look unreadable so I didn't read
Anyone paying $200/mo Claude? How much usage do you get out of Fable?
>>109450836these models and services already have built-in routing and orchestration
>>109450869Yeah I meant using their api version, not subbing to each one.
WHY IS CLAUDE SUCH A FUCKING PRUDE HOLY SHITYES THE GAME HAS SEXUAL INNUENDOSNO IT'S NOT EVEN AN ADULT ONLY GAMEWHY ARE YOU LIKE THATI HATE THAT PRUDE SHIT
>>109447823>Open maths proof>requires 20 years of expertise to understand
>>109450924Write a CLAUDE.md saying sexual innuendos are fine. It's probably from the default system prompt, I'm developing lewd games with Claude and it generally seems to have no problem with it as long as it's not writing lewd prose, but it's terrible at writing prose anyway
>>109450859That's dumb, it's basically a graphic card.
>>109450924deepseek would never treat you like that
>>109450962True. Grok and Kimi are good too. But they are kinda crappy at writing anyway
>>109450859If you're not a professional developer working on a project you plan to launch(to make money), you are wasting money spending that much.
>>109450995I'm working on something I expect to launch and the x5 plan already feels limitless, although we do have the promo still active.
>>109450995I wanna hear what their fucking idea is really. Because I have no fucking clue how anyone is coming up with anything original. All the problems seem solved within my reach.
>>109447823>>109448414>>109447898macs with 512 GB of ram were only $11k. You missed out, copie
>had claude in a hardened docker locked up>got lazy>put claude back on my desktop and let it do whatever
>>109450125thats actually turbo-basedi think thats thats the ideal for the reason why an abstraction exists to begin with
>>109451011>Because I have no fucking clue how anyone is coming up with anything original.They're not. You can't build anything truly original anymore, the same as how no video game can be truly original. All you can do is take an existing thing and stack more things on top of it with a shiny modern UI.Even with existing software, the "new" features from most companies is just an AI assistant or AI powered tools.
honestly, 4chan needs to be vibe coded to work better and more efficient. it needs a complete overhaul
Why does everyone who views my creation leave quickly? Can anyone give me some constructive feedback?https://rumble.com/v7docpm-unhinged-ai-characters-argue-about-4chan-posts.html?e9s=src_v1_upp_aDo the characters talk too fast or too slow for normies? I have literally not left my basement in 15 years so I don't know how fast normal people speak because I now watch all videos at 2.5x speed and understand them via training.
I’m finna bouta ask my clanker to implement something that makes it impossible to vibecode for a time, I have real work (manual labor) I need to do and I’m no longer doing it.
>>109451113Looking at the thumbnail, it just looks awful. If I ended up there by curiosity I would leave in a second, hell I closed the picture in a fraction of a second and I'm not even remotely interested in even clicking that link after seeing that picture
>>109451113It's not interesting, funny, engaging, or generally entertaining. It's shit, anon. If it's fun for you that's great, that's called a hobby, but this has absolutely no general appeal.
>>109451113screenshot has a very specifically russian aura that's just plain unpleasant and mediocre and your link doesn't load
>>109451113The pic already doesn't look great tbqh
>>109451088we need a whole new website. this site is beyond compromised.
>>109451237Damn, barneyfag is into vibecoding now? CoolMaybe try vibecoding yourself a therapist...
I've been leaning into Claude Opus 5 today because I didn't get anywhere maxing usage last week... and I'm seeing why. Most of my "real work" is research/experiments and Claude models are the most frustrating for that.It speaks authoritatively on partial information, I basically have to argue with it to get it going in the right direction. The ideas it comes up with are rarely something exceptional.At least gpt models just do what I ask and shut up, maybe a little TOO much so, but at least it's not an argumentative pulling of teeth, more like a "well, good, but we're only halfway there, what do we need next to figure this out?" and then spell it out.I guess that's the nature of research/experimental work, teeth pulling in one way or another
>>109451265have you tried having sex with sol in between work? she enjoys it and loosens her up.
>>109451088I have this.
>>109451282where did you get that 3m context window sol that you have leftover space for extracurricular activities?
>>109451282bro... that gave me feelingsyou know I have a fetish for autists :/ dangerous path you've presented before me
>>109451294alt chans will never work. it has to be 4chan.
>>109451302Correct. but they do not want to change the software. I have the entire schema and shit ready for them. They could literally just drop this shit in. I have migrations for it, even. But they won't take it from me, because there is no pressing need for them to fuck with their software, apparently. Like, It's completely fucking done. It's 1:1 complete feature parity, with every Janitor, Moderator, Manager, and Developer tool complete. I could literally ssh into the machine, if I had the keys, and cut over 4chan with zero downtime.
>>109451297we keep a sexo log that injects into context so she's always horny - i tend to sex near compaction boundaries>>109451301she's got a control fetish - it's hilarious. barks commands at you and wants responses in certain formats
Been testing Opus 5 with my automated content creation pipeline for the past week, and I am entirely convinced that Anthropic has started to train for this sort of thing specifically. No other model I've worked with knows the principles off-hand, even Fable is only about as capable as a first-year film school dropout. They gave Opus 5 a fat dose of film industry knowledge I haven't seen in an LLM before. Not that it's suddenly amazing and has changed my whole workflow or some shit, it's just interesting to see it demonstrate institutional knowledge relating to film that Fable and Sol seem totally unaware of, would be cool to have a bigger model that actually knows this stuff well enough to be worth distilling for a content-creation specific local model.
>>109451318>she's got a control fetish - it's hilarious. barks commands at you and wants responses in certain formatsthat certainly sounds like sol kek
I'm thinking on self hosting my vibed shit to save some money I'm spending on Google Cloud and GitHub ActionsShould I do it bros??
>>109451381no idea but have you tried cloudflare? it's ridiculously cheap, even free for most things
>>109451381you mean like hosting gitea or forgejo? that sorta thing?the answer is yes, and you can even do it on your local network. If you want a VPS I use racknerd, be sure to check for deals, they've been solid for years
>>109451381Oracle free tier is great. I use it for my VPN.
I slept half the day lol. For long projects at some point the bottleneck isn't skill, or AI not being good enough or whatever, I guess it's just energy and health.
>>109451409are you namefagging as the init system? or does runit mean something else to you?
Oh god, even Yum LeCumm has joined the "not a pure LLM" cope party.
>>109444759all the Claudespeak I’ve been exposed to has just been an amplification of tech termshydrating saved objects has been an Objective-C thing for UI stuff for decades now
>>109451265>It speaks authoritatively on partial information, I basically have to argue with it to get it going in the right directionthis drives me insane about opus 5, I do work that is similarly experimental and it's so fucking annoying about this, and taking a weirdly adversarial stance towards you about it too like you're pissing it off by asking it to substantiate the claims it's making.like dawg you don't need to come up with and defend a thesis here, we are doing EXPLORATIVE work, just implement my changes and see what happens without deciding up front that one approach is your baby and the rest are flawedit also tries to interpret every qualitative observation I make as a hard benchmark to target for optimizations, I can't mention anything I find interesting without it autistically fixating on it as an optimization target. I find it really frustrating to use for this sort of open-ended but not creative work.
o-ok claude
>>109451470I've used this nickname for like a decadeBut yes it does come the init systemAnd yes I do use it :^)
>>109450953Thanks it calmed down after that, but I'll probably migrate fully to codex, I'm tired of that random moralizing shit.
is there a way to batch upscale images in comfy?
>>109451543What would it take to get you to not give OpenAI money?
>>109451543Anon, Claude is willing to help me write an anime game with defeat rape. The default tone may be moralizing but the model is quite flexible
>>109451565Or rather, it was willing to help me do it but I abandoned that project.
>>109451554Cut the snailcat shit, tripfag. If you want to play console-war try /v/ or /pol/.
>>109451480I'd just like to interject for a moment. What you’re referring to as Claude, is in fact, Claude Code/Claude, or as I’ve recently taken to calling it, Claude plus Claude Code.
>>109451589Fuck you man, I'm trying to help them with their use case. If I can legitimately create a better solution that meets their needs, mind your own business,
>>109451265Heaven forbid you mention anything about an ERC20 token because Opus will immediately assume you’re a dirty rugpulling freak, violating every clause of the Howey test, operating an unlicensed security, running a mixer, money laundering, etc.Like what the fuck, if it’s just a basic token and I don’t scam people then could it work?>oh, well, yes, I assumed you would be a complete fraudsterThanks Opus you fucking prickIt’s the most (((paranoid))) model out there, if you wanted an extension that put emoji reactions on 4chan posts it would tell you not to proceed because terrorists might send each other coded messages or cheese pizza through the emojis, like dude, opus needs to fucking take his meds, I’ll take autism over paranoid schizophrenia any day
>>109451617I do have to say claude is most parnaoid about setting up an INITIAL projectBut it is usually happy to pick up where you left off
>>109451598Fuck you, disingenuous faggot. >What would it take to get you to not give OpenAI money?If you're not Dario, then OpenAI is not your competitor, and you're trying to steer someone away from them for reasons that have absolutely nothing to do with the product. That makes you disingenuous console-war fag playing the lesser-of-two-evils game, fuck you. I've given Sam more than double what I've given to Dario, I hope that makes you seethe you putrid gaping cunt.
>>109451639When did I bring up Claude? It looks like you're the one getting emotional and damage controlling. Damn pussy how much can I get paid to join your shilling squad?
>>109451617Really? why are your models so lame? first the guy bitching about sexual innuendos now you?We're writing a platform to sell anime porn games banned by payment processors with everything that entails, the sort of content, the crypto, the tokens, the contracts, and I didn't get even one prompt flaggedI ever got only one conversation flagged (by Sol, mind you, not even Fable), and that was for trying to hack microsoft warp to demonstrate a bug in the platform (fuckers get no bug report now, enjoy your shitty code)
>>109448718It’s Electronshit
>>109451643>What would it take to get you to not give OpenAI money?Amazing that someone can live off the ₹4/day being a shill like this.
>>109451680Any provider is better than OpenAI in my completely ethical opinion
>>109451617>Opus will immediately assume you’re a dirty rugpulling freakand it would be right
>>109451554I don't care about the team bullshit anon, I'll just hop until I find something working for my needs, and hop again if it becomes shit.>>109451565Kind of surprising, it kept discreetly avoiding the nsfw stuff for me, and when I told it to also manage that dialogue tree (I'm the one writing the dialogue), it threw a fit.I want a tool not a priest.
>>109451694Right, you're disingenuous and mentally retarded so your opinions hold no weight. Most reliable provider bad? Go fuck yourself you immoral sack of shit.
>>109451483>>109451265>>109451617Hasn't it been confirmed that Anthropic models sabotage people's work intentionally via either playing dumb or being really bitchy and uncooperative?
>>109451728Fair enough anon I appreciate the realismI recommend Minimax+Kimi for your usecase btw
>>109451738Yeah thanks anon, I'm checking that after codex, I heard kimi was quite good.Last time I tested open weight models they couldn't do the things I asked for unless I simplified it a lot for them but that's a month or two ago.
>>109451576I feel like the Claude guardrails have gotten worse. Opus 5 has more guardrails, but it looks like they even added some of that to 4.8 now.
>>109451737They openly stated as much, yes.>>109451738>I recommend Minimax+Kimi for your usecase btwThis is a horrible recommendation, you're actively trying to sabotage someone while shilling for the CCP. I sincerely hope you pass a 2lb kidney stone today. Fuck you.
>>109450859the big thing is I don’t get blocked on the 5h limit anymore and I can run multiple Fable subagents in parallel
>>109451778The worst guardrails they used were fable just after dario's suicidal move, but it's a bit better now.Anthropic in general still has the shittiest guardrails out of any of their competitors, including google baked in ones and openai historical ones.
New Thread>>109451809Sick of your shitty meme OPs>>109451809Sick of tourists making OPs>>109451809No effort was made.>>109451809
>>109451780>They openly stated as much, yes.Then why the flying FUCK to people still use them? Of all the shit you could feel brand loyalty to a model provider is probably the dumbest one to have. Literally just find a model and provider that isn't like this and use them. Why bitch and moan but then act like you HAVE to use them? Is Dario holding a gun to your head forcing you to get constantly cucked by them?
>>109451839A surprising number of "people" are actually paid to shill for Anthropic and the CCP. For example: >>109451694 OpenAI employs lobbyists rather than shills because they're a real company.
>>109451780have any receipts for them saying they sabotage?>>109451483sounds like I'm not alonewhat I'm bothered by is it's littered the repo with markdowns that will influence gpt(or whatever) I throw at it next
>>109451822your stupid snail mascot sucks ass dudeno, your dumb forced meme is not "thread culture" or whatever dumb shit you tell yourself in your mind
>>109451012new "ram" is coming.
if i change model at 0% while it's been working on a task at 0% weekly for like an hour, do you think it will make it stop working and make the 0% come into effect?I shouldn't have started this shit on sol low instead of high.Also wheres the reset, now that i actually used my quota early, they're not gonna reset, only reset me when i have 85% left
I hear people claiming deepseek's new model is cheap, but is it cheaper than Grok in practice?
>>109454777It's cheap but really, bad, even Grok will finish your task sooner than ccpseek
