X-1-0

@fxnction Best is codex xhigh. Codex medium is like Opus at the moment unfortunately until they fix it

Are people using GPT 5.5 as the worker agent or the reviewer?

Google Gemini results unfortunately been bad, now they invested in Anthropic. Hopefully Anthropic doesn’t let mythos keep coding it’s own software for now.

Opus dropped the ball for a while now and they just recently admitted it. Codex 5.3 has been the workhorse for me, 5.4 not so much, had to baby sit it. Since Opus was fixed, it started doing well in the last few days, however Codex 5.5 xhigh the current top model for me. Hats off to the team, it constantly finds and overwrites Opus’s decision. Hopefully @bcherny and the team can step it up. Gemini, not sure what to say. Seems like the team has been rushing to get something relevant out there but results have been poor. Interesting times ahead.

some random ai thoughts: - for code, i went from 80/20 claude/gpt to 80/20 gpt/claude in <3 months. surprised by this tbh, and interested to see where the split is at in another 3mo. - claude still mogs gpt for non-coding agent stuff. codex feels like an engineer (which is great for coding!), whereas claude still feels like a general purpose coworker. gpt still lacks that coworker magic - i’m pretty meh on opus 4.7. my experience hasn’t been *bad*, but it certainly hasn’t been good. sideways if anything. - anthropic has got to figure out the compute thing. you can feel it as a user. vibes are all out of whack bc of it. my opinions above are all likely downstream of this. it’s an issue. - anthropic labs continues to be the goat of ai product. claude design is another hit. it’s fantastic. idk why it’s not talked about more? a+ - updated claude code app is great. i finally switched out of the terminal for it. very well done. - how are people STILL sleeping on the claude agent sdk? i feel like i’m going insane. - gpt 5.5 is incredible. the level to which i trust it for engineering is amazing. if i could only have one model rn, it would be this one just bc of strong need for the coding use case. - codex team is killing it. app has been the gold standard since 5.3 release (buuut i credit conductor team for the ui innovation that everyone is using now). though i could do with a little less passive aggressive shots at ant from the codex team. TARS, dial up class by 30%. it’s a long race guys haha - i uninstalled cursor this month and am now back to vs code for my ide. composer just can’t hang with claude/gpt, and the product feels a bit all over the place. pretty stoked about the xai thing though, because their team is absolutely stacked and i’m excited to see what they might be able to do with that compute. codex and claude code are t1, cursor is t2. i would love if this deal got xai/cursor to t1 for a real trio there. - gemini…? seems like this is 2-3 models now where the model seems like a great release and then nobody ever uses it? i’m bullish google/deepmind but weird it hasn’t translated to product use in any form. kinda disappointed still - no open source models have hit the opus 4.5 level. was hopeful the new deepseek would get there, but nope. good oss agents will have to wait a few more months it would seem…

What happened to the X ‘for you’ algo - it’s all full of videos now. Not sure if it’s X or Instagram now.

@realmcore_ Been preaching this for a while. Codex 5.3 for me > 5.4/Opus 4.6

5.3 codex xhigh is significantly better than 5.4 xhigh for coding. It's genuinely nuts

StubHub needs to explain why World Cup tickets look “almost gone” while legit sellers are being blocked from listing. I have extra FIFA tickets for a match still 2 months away, accepted all seller penalties, and still can’t list while buyers get hit with insane prices and huge fees. Feels like artificial scarcity, FOMO, and price manipulation. Real fans are getting priced out of the World Cup.

@iamjesserichard Honestly this one looks much better x.com/x1_0_/status/1…

Introducing Tesla model W

@emmanuel_2m @Scenario_gg Used Opus to help me out in the beginning but Codex 5.3 has been the workhorse lately for me, even better than 5.4

@X1_0_ @Scenario_gg 👀 Looks awesome. Claude Code?

Small details, big impact. New in @Scenario_gg nodes: drag a connector, release anywhere, a dropdown lets you pick the next node... auto-connected instantly. And you can connect to 250+ AI models from there. Building node-based workflows has never felt this fluid.

Perhaps I should have finished it 🥹 x.com/axios/status/2…

Every technical founder who had stopped coding 10 years ago

@bcherny What have you done to Claude code today? It’s suuuuupeeeeer slow.

This turned out really nice. Excited to hear what you think! Install the Claude Code Slack app here: code.claude.com/docs/en/slack

Made this quickly almost a year ago. Wonder the possibility now w/ Opus 4.6 or GPT5.3

@claudeai /fast make me a billion dollar startup. make no mistakes

Our teams have been building with a 2.5x-faster version of Claude Opus 4.6. We’re now making it available as an early experiment via Claude Code and our API.

If you’re into AI + Design, you should be following Amir. Produces top quality designs.