"O" My !!

Gpt6 Astra billing today is completely crazy, eaten 25% of usage from pro lite in under 1h, And 25% of pro200 in ( under 2h) . For same session that yesterday was using less than 10% on same tasks. Using codex cli . Only. Yesterday chatgpt codex app and codex cli .

Astra feels Sol , even on ultra still does lazy stupid mistakes! Was it nerfed before devday? Or opus5.5 effect?

If gpt6-astra was as fast as opus or 2x ? And similaraly priced as sol . Welcome to gpt6.1 On dev day. Intellegence of astra , speed of spark and price of sol.

Openai always ON , must be just enabling event driven codex wake ups ( instead of static sheduled tasks), also if codex can be programatically called over any mcp api hook will be huge unlock.

Skill distillation is hybrid approach. Take it with lots of grain of salt. It is like building software .

Gpt6 pro users be careful with your pro model usage, it is no longer the old fair unlimited. It is now hard capped ( at least some transparency) but very disappointing limit of 200 messages , yes 200 per WeeK !! Not per Day !! Gpt5.6 (underperform gpt6 extra high) has more usage, 170 per day. But unusable . When will openai make gpt6 pro default pro model at 170 messages per day as was 5.6? @OpenAI we need pro model usage back to 170+ per day !! You are damaging researcher, Iam competing for kaggle arc ag prize hackaton , but run out of pro messages hours ago . @OpenAIDevs @thsottiaux @gdb @sama

Sorry openai , real gpt6 is astra , sol looks like a renbanded 5.6 with no jacket

elevated codex errors happening on gpt-6 sol . definetly gpt sol 6.1 is moving fast deployment to respond to opus 5.5

gpt6sol is at capacity. surely 6.1 is cooking for next week.

last chatgpt app mac build is incredibly fast stable and agile. update immediately.

I was using 4 computers with 6 screens , now i only use my phone. Thanks chatgpt.app for mac and linux and windows. And ios of couse.

Ternus to zuck : thank you for the little steer, on the way with next vision lite wireless with iPhone maybe even with the patented decade ago wireless remote charging tech. So the next apple vision should use only display , and some really small battery , all the power battery and compute will come from iPhone wirelessly or with a tiny cable.

Oh my ! Gpt6 sol is unsupportedly annoying to interact with , worse than astra , if astra does what it sees the righ thing for your need but respects ur specs and output , sol does neither, you tell him paint this honda in blue, it brings you a dark horse. If i renew my claude it will be because of that.

anthropic look they time their new model launch exactly when people tend to renew their max subscription, so they get them to renew. i had a zest of opus5.5 a very nice model. worked perfectly the first 24h . not guaranteed to not be nerfed as previous models, or we adapt in a hedonic treadmill way. or learn it is another liar. i didnt renew my max20 subs. my factory is built around the great chatgpt desktop/codex and codex app server/sdk /symphony. i dont feel i missed anything for now. simply because a real factory dont need lots of ping pong with a silly distracting agent over a cli. my next pro subs will go to chat again, you are late to the game misanthropic. many of use dont trust you anymore. waiting for openai to open pro200 subs again . question is when ?

claude having issues smells new model deployment :● API Error: 529 Overloaded. This is a server-side issue, usually temporary — try again in a moment. If it persists, check status.claude.com.

sad and happy at the same time, my factory just solved mid-high vulnerability gitlab issue ( was testing it for security) , solved in under 1h. submitted . validated but duplicate ( not available publicly) . so my factory did it . just i didn't inspect the issue deeply for previous work. next one will be a hit. a big one.

sad and happy at the same time, my factory just solved mid-high vulnerability gitlab issue ( was testing it for security) , solved in under 1h. submitted . validated but duplicate ( not available publicly) . so my factory did it . just i didn't inspect the issue deeply for previous work. next one will be a hit. a big one.

Your coding agent re-reads every old log, build dump and file it has ever seen. Context Diet clears the junk and keeps what matters, without you changing a thing. A month of my usage: ~1M tokens of clutter gone. $0.14 on Jev, or free on the local model. github.com/konstantinosboton…