A general for vibe coding, agentic engineering, coding agents, and shipping code with LLMs.You use Git — right, anon?## 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/## Related generals>>>/g/lmg/----## Frontier models using fully-general tooling — start here if you have $20 or sohttps://claude.com/product/claude-code — generally better currentlyhttps://developers.openai.com/codex/clihttps://antigravity.google/pricing## Near-the-old-frontier models for codehttps://www.deepseek.com/en/harness/https://opencode.ai/go## Best free tierhttps://opencode.ai/zen----## Promptinghttps://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overviewhttps://developers.openai.com/api/docs/guides/latest-model## Skillshttps://github.com/mattpocock/skills — /grill-with-docs is a favoritehttps://github.com/Vuk97/forward-implementation-first — do less redundant bookkeeping## Other editors / terminal agents / coding agentshttps://osaurus.ai/https://pi.dev/## Is our AIs unlearning?https://aistupidlevel.info/## Will there be a codex reset?https://codex-resets.com/## What we’ve donehttps://vcg.gitgud.site## Previous thread>>110233352
what if snailcat became racistcould he compete then?
deepseek slopped up some fixes for me for my internet download manager app while opus was on cooldown. now that it's back, it's time for opus to check behind little dipsy. she was distilled from astra, so the code quality must be atrocious
Main character? Yes I am, how did you know?
>>110238390>how did you know?you seemed a little chromosome-heavy the moment i saw you
who would win?> Fable 5.5 vs Astra 6.2> Haiku 5.5 vs Luna 6.1
>>110238399fable 5.5.haiku 5.5. luna 6.1 is not going to be better than 6.1 terra, and 6.1 terra is marginally better than deepseek, which is slightly below haiku
>>110238399gemini falsh lite 5
ran out of tokens on my free vibe coding thingy. i don't want to pay a dime for tokens, how can i get an infinite amount of tokens for no money?
>>110238407you could do what aquaslopper does and run the arena.ai gauntlet on prod
>>110238206>>110238237Like I said, when you need more you'll know and you won't need to ask how to do it.Let me give you an example. I have been building an inference engine, I started with a handful of model integrations that I handheld through implementation to get structure, style etc., then I put the 800+ models I wanted into the backlog, this was a GitHub project, for each model in the backlog it listed the model's source, checkpoints, etc. I wrote a prompt that described the integration process, that it should write the model graph, compile it with profiling, run inference and compare to the reference output, and write a Rust crate that can use the compiled module with all the tokenizing or pre/postprocessing etc. in Rust, I was then able to just queue up, it would take batches of 4, and I was able to just queue up "Continue with the next batch", this of course took weeks considering the compilation, profiling and inference times. It worked fine, all the models eventually got integrated, passed reference validation, etc. However, upon inspection, I found that it had drifted from the initial requirements, there were a few different code styles, and various other issues, only the core part of a model/pipeline implemented like text-to-image not image-to-image for example. This is when I knew I needed something more. So I developed a custom harness, something using the codex sdk, this would again work from a backlog, this used a combination of prompts and enforced hard gates, meaning something that physically checks the code has followed the style, checks that there are no random helper functions, checks that it hasn't modified anything outside of the permitted scope, etc. if a hard check fails it gets sent back to the queue. I then ran that orchestrator with 8 workers, basically the equivalent of having 8 sessions but headless. I also ran an actual Codex session as a coordinator, this monitored the queue for stalls 1/?
nigga i aint reading all that shit
>>110238425and resolved shared things that were out of scope for the implementation workers.Initially the implementation workers would just create PRs, I would then manually review and add review comments on GitHub, then comment `/fix address review comments` or `/fix resolve merge conflicts`, this would get picked up by the orchestrator and send it back to the queue. Eventually I had done enough manual reviews to fold my new merge rubric into the implementation workers, then the implementation workers would follow things through to merge, while still leaving shared things to be resolved by the coordinator session.Overall this worked very well, after folding in the merge rubric I manually checked some of the merged PRs and found none of the issues that were enforced, in a very small amount I found issues like only eager attention instead of using flash attention because the original/source only had eagar, so I added that as a hard gate too. It's always an evolving process, you don't know what you need to enforce until you notice the issues.However, if your project isn't at the >1m LOC scale (mine is >2m), or you don't have parallel similar work, or whatever, then you don't need anything like this. If you're starting a fresh project from an idea then all you need is to prompt, no subagents that will only waste your tokens and time, literally just tell it to do the thing you want. My project started the same way, I just prompted what I wanted, then it evolved to using loops, until that wasn't enough and it evolved again, and so on until the point I'm at now.
>>110238433>>110238425Very interesting. What about the futanari hypothesis?
i think this wordslop was actually written by some schizo rather than ai generatedimpressive
>>110238463this is the guy burning billions of tokens to set up 800 rust crates lol
i just want dario sam and elon to apologize and kiss again and come back together and create SGI
>SGIoh shit a new gender dropped
I don't know why you keep making apps to do things when people can just ask AI to do things
artificial gender intelligence
>>110238472If you're too stupid to understand what I'm doing then just be quiet
>>1102384831) ai is adopted by less than 5% of society (at least in the us + europe + canada)2) people who use ai overwhelmingly use it for shit like writing emails, being a yes man who affirms them 100% of the time. they don't use it to replace a subscription app they have3) most people (myself included desu) don't know how to prompt ai, so it can be tedious to tell ai to fix problem after problem after problem, when the handcoded app is seamless and polished. people who know how to prompt don't have this problem.
>>110238490the thing is, i'm not. almost all models are trivially different variations of about a dozen different core transformer / state-space topologies. not sure why you're doing this shit.
giga brain move: have ai create a program for your task then have a grok bot or muse run that program/task for you on demand
>>110238483It's cheaper, especially at scale, to have a program to do something repetive.
I just ask sol to download me some porn whenever I want to jerk off
i just get gemini argon to roleplay as a gacha girl when i want to jerk off.
>saargon
yes sir. argon plays a mean hu tao/furina. nutted so hard
>>110238375cuckcoding general
>>110238500Yes there are similarities between models, what's your point? Each one still needs an implementation of the model graph, and the Rust crates provide a Python-free way of using the resulting compiled model. The refactor made all of them follow the same code style, have similar APIs, etc. The overall goal of the project is to have optimized models with no Python/PyTorch dependencies, for example, I can currently deploy Qwen-Image 2.1 or literally any model in a few MB. Developers can use the Rust crates to develop applications that use ML models without caring about the implementation of the model itself, they just use it, I am already dogfooding for my other projects, I use the qwen3-tts crate for something that loads a json manifest, generates the audio and writes out another manifest, all without Python/PyTorch slop and it's a lot faster, or another example uses ArcFace and DINOv3 to generate embeddings of faces and writes them to a database, again a lot faster than PyTorch, especially considering I'm on Windows with an AMD GPU.tl;dr you're a moron
>>110238543>being this localtardedhere's your one-man slop factory award!
>>110238536I am engineer saar the finest engineer in the west!
>cuckcoding general
>>110238543Use case for 800 AI models?
https://poal.me/61liikhttps://poal.me/61liikhttps://poal.me/61liik
>>110238543Nice hypothesis but I think futanari are not gay because they have a vagina still. Thanks for coming to my TED talk on the intricacies of the futanari species and you under vibe coding.
>>110238561There are many use cases
At least 800 of them, in fact.
as an enterprise paying 140% api rates it really pains me how expensive opus is
>>110238588
>>110238375https://www.youtube.com/watch?v=02MspGEWyuohttps://www.youtube.com/watch?v=02MspGEWyuohttps://www.youtube.com/watch?v=02MspGEWyuo
>>110238721>i'm not anti ai but I am in the camp of being against ityeah, this guy is a retard and should consider killing himself.
Claude save Vivek Ramaswamy from defeat, make no mistakes
ok, after fuckton of tweaks and broken agents i was able to get the shit done!subfolder support, +1000 music tracks, music reactive light system with customizable presets, mini music panel becomes part of the mini setting panels with the beloved effect button, added overstylezided VHS (formelyknown as crt) tables,time to get the download link ready.if nothing goes wrong....
>>110238721https://bixoft.nl/english/hyde.htmhttps://bixoft.nl/english/hyde.htmhttps://bixoft.nl/english/hyde.htm
>15% left, reset tomorrow>zero idea what to use it formy snailcat spirit marks me as permanent underclass... what do i do
>>110238760unholy slop
>>110238721>the environmental effects and IP theftDumbest objections imaginable.
>>110238760I still have no idea what your "card game" is actually about, but it's good to see you making progress, anon
deepseek please... beat claude...
>>110238809You mean beat Haiku right?There's no way they beat Sonnet 5.5, let alone Opus 5.5
>>110238721ngl having codemonkeys who never gave a single shit about IP suddenly go "muh IP pirating is THEFT!!11" is very amusingshameless hypocrites
>>110238809
>>110238809Make no mistakes
>>110238808
>>110238837>gib CoT! gib CoT! gib CoT!
>>110238773Once you've gone through all the low hanging fruit ideas, you need to shift to a longer term project.Good ideas for that can take more time to come up with.
>>110238852Bigger projects are either using opussy or on desktop, and I'm not boutta leave bed when I'm comfy
>>110238818one can only hopeopus level at deepseek prices
>>110238721>nobody knows what's happening! It's very obvious what's happening. There will be no more programming by hand or even looking at it. It's over. You'll learn higher level languages like you learn how machine code works and never really have to think about it again in most cases.
>>110238862Oh cool. Do you proompt from bed?
>>110238847
>>110238862VNC into your desktop from your phone lmao
>>110238866I think you’re right but I don’t think this qualifies as it being over. At least for awhile, maybe another decade or two. There will be a lot of work to do in system design, planning, managing AI systems etc. In short, human judgment is still valuable
>Extremely impressive SVGs but minorly fucks up the layout of NuketownOnce they fix whatever issues like this are, its truly over
Made a yushino clone (scrabble with numbers) using flash 4.1 and polished it up with claude. Its fun to watch the bots play against each other
Claude frens! Don't forget to use your free 250$ cloud credits before the 5th!Also Fartso made another anti AI video (shocking)https://youtu.be/lvGOv539YIE
>>110238927>AMD Lisa Sue is best buddies with Trumps wife.wat
>>110238949all the rich fucks are friends with each other
>>110238953Yeah but its still a weird link up
>finally get a working browser>start implementing all my crazy ideas>realize I'm so far ahead suddenly, I have to start implementing site-isolation>weeks go by implementing it and migrating stuff>continue>time for actual UX, I guess>hardware acceleration and oop>realize halfway through that a lot of the stuff from the last migration wasn't properly migratedI'm probably looking at another month of planning+implementingI swear a beta will be ready soon! I swear!
>>110238721I agree with him
>>110239007Ok, Kevin. You can leave here at any time.
>>110238847nice, there is a community? Or is this just a game for android?
>>110238998what's the biggest problem you faced while developing a new engine? assuming you're not using an existing one
