EnPassantGuy
190 posts
EnPassantGuy
@enpassantguy
Former CTO turned Software Engineer. Serial Builder. Rarely ship anything though. Founder of En Passant - an app focused on learning chess openings.
United States Katılım Şubat 2026
61 Takip Edilen4 Takipçiler
If only there was a good, high quality, open source option that worked with all vendors 🤔
vas@vasuman
Betting your entire AI stack on one vendor (OpenAI, Anthropic, Google) is the worst decision an enterprise can make right now. Price hikes, quantization, rate limits, migration costs are all coming. You need to abstract your model layer or you'll start to feel the pain soon.
English
@theo Supporting all of these under one hood is an achievement in itself. No other tool is doing this.
T3Code is gonna blow from here. Many devs like myself have subs with codex, claude, and cursor.
Only question is how do you monetize this?
English
@theo Don’t worry Theo. The “humans behind the apps” will forget the praise quickly.
English
Took a bit of effort but you can absolutely get good designs out of Claude Design. Hats off to the team, I dig this.
Theo - t3.gg@theo
Really liking Claude Design so far. Except for the fact that it just wiped out my project after burning 10% of my usage. "The files appear to be gone" 🙃
English
@claudeai Also Cerebral Valley will turn around and sell your information afterwards.
English
@claudeai Never applying for a hackathon like this again unless you can clearly define your process for selection.
It’s not random and mostly seems biased from what I’ve been able to discern.
English
The Claude Code hackathon is back for Opus 4.7.
Join builders from around the world for a week with the Claude Code team in the room, with a prize pool of $100K in API credits.
Apply by Sunday: cerebralvalley.ai/e/built-with-4…
English
people shit on anthropic and claude but this is what codex thinks is good design
what the actual fuck is this list my fucking god
please codex team i beg you let me unsubscribe from anthropic
deliver something good with 5.5
English
@dudufolio They learned from Cursor. The king of mid-day updates.
English
@MilksandMatcha @cerebras Really want Windsurf to make comeback and compete in the market.
More than happy to post my experiences while using the $200 plan and share cool things I’ll build with SWE 1.6!
English
Giving away 5 Windsurf Max ($200/month) plans
Each person will get 3 months of free Windsurf Max (highest tier). Try out SWE 1.6, Cognition's latest, fastest, and most intelligent model, powered by @cerebras.
Winners will be selected from comments in 48 hours, comment below why you want it.
Cognition@cognition
We’re releasing SWE-1.6, our best model in both intelligence & model UX. SWE-1.6 matches our Preview model on SWE-Bench Pro while dramatically improving on various behavioral axes. It’s available today in Windsurf in two modes: free tier (200 tok/s) and fast tier (950 tok/s).
English
EnPassantGuy retweetledi
Designed this with Claude in 20 minutes 😱
yeah, we’re cooked
Claude@claudeai
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
English
@haider1 I mean they publicly announced increased limits to help. Though they did not specify to what extent.
English
opus 4.7 is a rushed release
gpt-5.4 is still outperforming opus 4.7 and now we are waiting for gpt-5.5 any day now
4.7 is good, but not as good as i expected after anthropic nerfed opus 4.6 -- and it is using about 1.3x more tokens while they quietly reduce the user usage limit
English
@heyandras Yup. Seeing the same. I’m actually liking it better than gpt 5.4 right now.
Front end capabilities got a big increase too
English
why it could be that opus 4.7 experience is soo different for everyone?
i built a very complex new app (rust based) with it, and it was almost one shotted everything.
English
EnPassantGuy retweetledi
I didn’t think I’d be saying this, but I’ve been testing Opus 4.7 versus GPT 5.4 on some tough bugs at work.
Opus 4.7 High is outputting far more detailed feedback about the findings along with the correct solution for all 3 bugs I gave it.
GPT 5.4 XHigh only confirmed 1 out of the 3 bugs and said the other 2 bugs were not bugs.
Anthropic seems to have cooked. For the first time in a couple months I’m opening Claude Code first instead of Codex.
English
@enpassantguy @plugdotdev @davis7 They don't make money from awareness, they make money by lying in their outbound.
Awareness will kill them.
English
Just learned of yet another agency pretending to represent dev creators they have never talked to 🙃
English
@theo @plugdotdev @davis7 You’re giving them free publicity. Never would’ve known they existed otherwise.
English
Fuck it, doing call outs now.
@plugdotdev, stop pretending to represent me and @davis7.
We have a significantly better pipeline than you. We help brands more than you. We get COMICALLY more views than all of your talent combined.
To any talent currently trapped on Plug, my DMs are open. I'm happy to help you leave and work with an agency that doesn't lie to brands. You'll likely get paid more too :)
English
Serious question. Has anyone ever noticed meaningful regressions in Codex/OpenAI models?
I feel like we talk about this a lot w/ Anthropic but I've never seen a similar discussion with OAI.
English
@JJeffrey100 @ThePrimeagen Supposedly the latest CC update should fix this.
English
@enpassantguy @ThePrimeagen i noticed that too in stdout... has to be an injection check or something.
English
So everyone hates 4.7?
Yeah I hate it too, totally. It's just the worst.
English
@trq212 @ClaudeDevs solid move. Some actual DevRel for the billion dollar AI lab... which genius thought of this?
English
We’ve heard your feedback and we’re working on making it easier to follow everything that’s happening with Claude Code.
First, we’re introducing @ClaudeDevs, the official channel to follow for all updates on Claude Code and the Claude platform.
ClaudeDevs@ClaudeDevs
For the developers building with Claude, a direct line from the team. Follow for changelogs, API releases, community updates, and deep dives.
English