kk

only 5.6 sol high is decent at frontend

@argofowl build a T minus countdown my bro

about 4 hours to go until we get gpt 5.6 in codex 🌞

sonnet 5 is making spelling mistakes and typos AGI is achieved

slopmaxxing

@rezoundous don't disturb them, they are busy building agi

Dear Gemini, are you gonna join the race anytime soon?

@chiragdotxyz using it to do web search and use gpt 5.5 pro via github.com/steipete/oracle

anyone still copy-pasting code from ChatGPT?

@corbin_braun i think its more about the pricing than caring

fable 5 is making me realize that when AGI is here. 99% of humanity still won't use it or care crazy.

@kapilansh_twt just like sonnet, after the release of fable, i think opus is also gonna jump versions opus is the new sonnet

after Opus 4.9 Anthropic has no choice but to release Opus 5

ofc it is

having a proper file/folder structure matters a lot for ur agent to work on, maybe even create an index md

@pcshipp progress

Since AI started writing most of my code, I've become too lazy to make even small code changes myself. Some days, it feels like my coding skills are slowly fading away.

@droidbuilds it already does lamaaaaoooo

Devolopers, what’s your backup plan if AI starts writing better code than you in 2-3 months?

workflows ultracode workflows ultracode workflows ultracode

Today is the last day to use Fable 5

@scaling01 gpt5.5-cyber wen

LisanBench results for Fable 5 I've actually withheld LisanBench scores for like 2 weeks now, because honestly starting with Opus 4.6 the benchmark in its current form. Overall, Fable 5 scores #3 and #2 in the main path length and difficulty weighted metrics, but it's not meaningfully better than Opus 4.7 and Opus 4.6. This has two reasons: - Opus 4.7 was tested with xhigh thinking budget, so scores are naturally higher than just medium. With equal budgets Fable would likely score higher. - Opus 4.6 was one of the only models where I could find reward-hacky (I have written an article about this) Fable is slightly more explorative and has a slightly higher fraction of legal moves than both Opus 4.6 and Opus 4.7. But on issue I found with Fable is that it generates a lot of invalid word transitions. Instead of just using edit-distance 1 it uses edit-distance 2. This happens ~28% of the time, for Opus 4.8 it was 0%, and Opus 4.7 and Opus 4.6 were at 4.7% and 13.3%. Often it used transpositions, which are invalid: fist -> fits or tied -> tide I have also moved to a more comprehensive dictionary, because the old dictionary was stopping the chains on english words, that weren't in the dictionary. This issue still persists, although it's much less common and doesn't affect ranking too much. If we allowed those words than its score would improve by +165.67 points, which wouldn't change its ranking. There's one hack I've done to make Fable 5 look good by taking only the top 10 hardest words. Because most starting words are just way too easy and models just farm points (see image 1 with table for scores). Also on the number of total valid chains, which also includes chains that happen after the official scoring stops due to an invalid transition, it scores #1. Overall I would still say that Fable 5 is the best model if you take the token budget and reward hacking into account. I think Opus 4.8 and other non Anthropic like GPT-5.5 also support that Opus/Sonnet 4.6 and Opus 4.7 are outliers. But I also see how this interpretation could be seen as cherry-picked.

@TheRohanVarma the fact that codex cli and app session history is separate is beyond me

If you were primarily a CLI agent user and switched to the Codex App: What got you hooked? If you haven’t switched, what kept you in the CLI?

@sama @ChinmayKak

We want to help all companies be secure, working with the USG and the security ecosystem. *The full version of GPT-5.5-Cyber is here; state of the art performance on CyberGym. *Patch The Planet and Codex Security will help solve security problems instead of just finding them.

@YesKhush_5 @boardyai when someone starts using animate pronouns like "his" for an ai agent, u know that the agent is awesome good job boardy!!

I'm joining the Boardy Pro Advisory Board! Will be working closely with @boardyai and his team to shape the future of Boardy Pro. Happy to share exclusive 1-year access to Boardy Pro for free. Let me know if you want one.

the best agent products won’t ask for less permission they’ll ask at the right abstraction level shipped an important ux + trust fix in our agent today instead of asking for approval on every small tool action, it now creates a 12 hour lease around a user’s approved intent so once intent is approved, related tool calls can continue within that boundary without repeated interruptions this makes the product better in 3 ways: - smoother ux - tighter, time-scoped security - more user trust because approvals behave predictably

gta 6 is cool, but what about red dead redemption 3