A general for vibe coding, agentic engineering, coding agents, AI IDEs, browser builders, 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/## News (both past and future)- 2026-09-28 — Anthropic releases Sonnet 5.5- 2026-09-22 — OpenAI releases GPT-6 Sol and Luna- 2026-09-22 — Anthropic releases Opus 5.5- 2026-09-22 — Anthropic increases subscription plans's 5-hour limits by 20%- 2026-09-14 — Anthropic reduces subscription plans's weekly limits by 17%- 2026-09-12 — Anthropic suggests to pace the frontier. OpenAI agrees in principle.- 2026-09-10 — OpenAI pauses new sign-ups for their $200 subscription- 2026-09-04 — OpenAI releases Astra- 2026-09-01 — Anthropic releases Fable 5.1## Related generals>>>/g/lmg/----## Frontier models using fully-general tooling — start here if you have $20 or sohttps://claude.com/product/claude-code — probably generally better currentlyhttps://developers.openai.com/codex/cli## Near-frontier models for codehttps://x.ai/cli — no 5h limit for only $30/month## Not worth it for code, but maybe good for interpreting images/videohttps://antigravity.google/product/antigravity-cli----## 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/https://opencode.ai/## 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>>109933222
ClownAIJewbo
>>109935982
>>109935982>AI IDEs, browser builders,Does anyone give a shit about AI IDEs and browser builders?Besides, when I read “browser builders”, I think of https://x.com/awesomekling — not building stuff IN a browser
ok anons, who do you give money for>good models good usage from the cult of doom>weak models from the righteous chinese men of no compute>shit usage from a SAAS company but just 2 months away from AGI
>>109936023I give money for Nvidia and the power company, doing inference locally. The more I buy, the more I save.
>>109936023
What did you vibe today? I let space bunny try to get MiniMax H3 working on my phone. It succeeded at a 2bit quant. This is what success looks like.
https://x.com/thsottiaux/status/2104823812042940713> it will net out at half the dollar in API spend compared to the old Pro $200 plan.I hope today they release a new model and this will only apply to it...but maybe not, so it will be x10 instead of x20, yes it's fair price but now it has no edge over claude subscription anymore
>>109935949lol I'm fucking done with OpenAI, goodbye faggots. GrokBot is not worth $200 while cutting my tokens in half. These idiots are high on their own supply. I'm switching over to Anthropic for good.
>>109936048>for goodanon, emotional brand loyalty is pathological.
>>109936048You are like 6 months late with that decision...
>>109936048>>109936053yeah, I’m a Claude enjoyer but if Sam released a model that gigamogged Claude and its workflow-creation tooling I’d switch
>>109936072workflow tooling from deepmind is probably the best in the game rn, just needs a model to go along with it
>>109936053OpenAI are waving the white flag. If they can't beat Anthropics models, they're going to try and win over customers with bullshit tools like Meta Muse. I need these models strictly for coding while I'm awake and can monitor them, nothing else. >>109936072I'll come back if they pull off a hail mary (increasingly unlikely, they pulled ahead once with Astra then got BTFO less than a month later by a rivals second class model).I think for a time I accepted that ChatGPT was worse simply because they gave me more usage. Now that that's no longer going to be the case, I can't think of a SINGLE reason to stay with them unless you reverse engineer.
damn these bitches lost all aura within 7 days
>>109936093for me, it was the constant stream of jeets and foids that work for them saying "immaculate vibes saaar... you gonna like tomorrow saaaars." nonstop on xitter
One of the anons here vibe-coded something that smooths out lines in an image editorI have a question for himwhat’s that kind of thing called? what should I be asking my clanker about to get something that will smooth out bézier curves by going back and forth with a pen over the path?
Is Sonnet good?
>>109936117use case for sonnet?
Has any of you used JEV?
>>109936201>I'm surprised we kept grokbot under wraps saaaaarI literally cannot wait for the nonstop humiliation ritual as everyone cancels their subs tomorrow. They are fucked once Fable 5.5 drops
>>109936201wish I was so above the law>yes I sold you ten pounds of $thing, but now the $200 subscription tier only offers two pounds of $thing
>>109936201>our models are worse but at least you get less usage!
>>109935982OpenAIbros we got too cocky
>>109936201 Hi,Tomorrow we are re-opening the Pro $200 subscriptions to new subscribers, but together with it we are also changing how we calculate the usage for it. In effect, if you do the math, it will net out at half the dollar in API spend compared to the old Pro $200 plan.Now that it's said, let me explain why this is happening and why you will still get more work done than if you were on the Pro $200 subscription one month ago.(a) We didn't want to compromise in other ways and are committing to not reintroducing the 5h limit, so that you can fully use the weekly usage when you want.(b) On the subscription, we guarantee that over time you always get more work done and with an increasing level of quality. This means that you will continue to get more value per dollar spent as a result of models getting more efficient and us passing down the improvements in the form of API price reductions.(c) We don't want to put an incentive on ourselves to artificially inflate the API list prices to make it look like you are getting a lot (and workaround it through discounts, etc). Instead we want to continue to both rapidly reduce prices and increase capabilities of models on the API. This week we introduced GPT-6 Sol and GPT-6 Luna at 50% of their previous price. Over time, we see prices go low enough that it makes sense for most to buy usage as needed without there being a significant gap between what you get in a subscription and what you get in the API for a dollar spent.(d) Tomorrow, we are adding more things to the subscription that won't draw on the usage, I won't reveal what that is yet.I wanted to be transparent before all the big announcements tomorrow. Lots of new exciting things are coming to the subscriptions that will make it super compelling, but I wanted to make sure to share this change ahead of time so you can all understand it before we shower you with good news.Codexingly,Tibo>tldr: what are you going to do, switch to claude?>o no
he think they can overtake opus by tonight?
>>109936231I have a 5 hour limit on my 20 dollar
>>109936252Sure, if you buy the $500 plan and pretend it cost $100
Price wars are usually bad before an IPO
>>109936231dario winning biglywhich is bad for everybody, since if cuckAI isn't competing then misanthropic will also lower usage
>>109936252even sol beats opus if you set it to fast modeastra beats opus hard
>>109936296what is this a benchmark of
these niggers really think grok-bot but gpt sol is + a reset is going to makeup for their embarrassing lapse in maintaining lockstep with anthrodick.grim
my machine is humming and the usage is being consumed at 20% an hourbetter use all the resets before the nerf
>company gives me api key>tells me they encourage employees to experiment with AI>use key for all my personal vibe coding>totally unaffected by usage cuts on sub plansyou should all just get good jobs
