@bytes032.xyz

@LLMJunky not the ceo bruh

@gmoneyNFT its called plansturbation

i gave it a shot, but can't do this anymore. hermes sucks ass. all these agents suck ass. they just stop working all the time and then take forever to debug. sticking to claude code and codex in terminal. far and away better than messing with this productivity porn

Cursor raised $2.3B to resell a open source model

@0xpupul obligatory like

I stay getting 0 likes, no one getting in my booty hole

@MartinMarchev this is my quant

@z0r0zzz @cantinaxyz @Certora @joranhonig bro single handedly created audit bench

added @cantinaxyz scan + @certora formal verification + @joranhonig grimoire skill run making moloch/majeur the most AI audited code - ever.

@eurofounder spot on

My daughter came home with a black eye yesterday "Dad, Ahmed hit me" she was crying I sat her down immediately "Sweetheart, you need to understand something" "Ahmed comes from a different cultural background" "He's still adjusting to European norms" She started sobbing "But papa, he punched me and called me a slut because I wanted to wear leggings" My wife pulled me aside and told me to call the police "And ruin a young man's integration process?" I asked We are a tolerant and inclusive European family I won't let one incident change that

You changed your agent. Did it get better or worse? If you can't answer that with data, you are not engineering. You are guessing. Here is how to stop guessing 🧵

@WildcatFi wen token

the codex team ships on weekends claude code doesn’t it’s pretty clear who wins in the long run

looks like sales is not going away soon huh

@banteg its surprisingly good with ruby

i expanded this eval to 25 languages and evaluated gpt-5.4 medium /fast in codex you can see the full results below github.com/banteg/minigit…

Your biggest value addition to AGENTS.md is: Bugs: add regression test when it fits.

junior auditors in shambles

insane numbers

@soveryisraeli 😂😂😂😂

I met an Iranian man in Luton Airport. He was in tears. Asked him what was wrong. He said: "My family is trapped in a literal battlefield. There's violence in the streets, killings in the name of Islam, collapsed public infrastructure, the government are all criminals..." I told him to keep strong, we're all praying for the citizens of Iran. He looked confused. "Iran? Bro, I live in Birmingham."

Latest V12 results on EVMBench (detect): 70.6% recall GPT and Opus achieve ~40%, 45%. EVMBench has a lot of problems. The grader is extremely flaky. Doesn't really measure FPR. No holdout set, invalid bugs. But anyways we're approaching saturation 😈🚀 More gains yet to come

@thsottiaux It would be great when the TUI gives a file path, when I cmd + click it would open in my default editor. I think this is big QOL improvement.

Speed and front-end capabilities: we heard that loudly, and things are improving quickly, to the point where I think we are now highly competitive on speed, if not best-in-class. What else should we improve for Codex?

@gakonst hatchet is pretty decent lightweight temporal alternative

github.com/earendil-works… github.com/earendil-works… extreme alpha in these two repos imo