Zuko-高考

@pyronaur @0xRemakw @thsottiaux What is this Pi ?, is it like opencode ?

@0xRemakw @thsottiaux No, they're stable. Running 3 sessions in parallel today all day and barely ate 10%. Optimize your harness. Whenever I use codex app it eats tokens for breakfast. In Pi I cant barely move tokens.

CODEX LIMITS REDUCED 50% can someone verify if this is true ? @thsottiaux

@zoeysandel @reach_vb @jxnlco @thsottiaux Hi, i did tell codex cli to nuke my Codex app and i think it did fix the user experience, previously i cant even navigate properly without having to wait for 6s, but now its running smoothly again, maybe its because of large thread that i have

@Zuko215 @reach_vb @jxnlco @thsottiaux Any chance you solved this?

@thsottiaux codex app is running very slow on my m5 after the update t.t, everything feels sluggish

Millions of clinicians use @ChatGPTapp every week to support care. Clinician use has more than doubled in the past year. To help physicians, NPs, PAs, and pharmacists get more out of ChatGPT, we’ve introduced ChatGPT for Clinicians, a free version tailored to support clinicians in delivering high-quality patient care, Our latest GPT-5 models achieve our highest levels of safety and accuracy on OpenAI benchmarks, along with strong results on third-party evaluations including @Stanford’s MedHELM and MedMarks. We’re excited to keep building tools that help clinicians move faster through admin work and focus on delivering high-quality patient care. openai.com/index/making-c…

@OpenAI S = Spud or S = Sam 🧐

This is not a screenshot.

@gdb how can i get the access ?

Announcing GPT-Rosalind, our frontier model for life science research. This model is a step towards one of our most important goals — accelerating science and improving human outcomes. Excited to work with many amazing partners on deploying and improving this model.

@jxnlco 👋🏻

How many people are using OpenAI Symphony?

CODEX FOR BACKEND (5.4 X-HIGH REASONING) CLAUDE CODE FOR FRONTEND (/frontend-design skill) ENSURE CODEX DOES TDD FEEDBACK LOOPS (its great at this) HAVE CLAUDE CODE GENERATE DESIGN VARIATIONS this is the meta i'm coding with rn

Quick reminder that @trq212 or anyone from Anthropic hasn't responded with a simple Y/N to this. Instead, we have Thariq posting about t3code, and deleting right after... ig the lawyers didn't like it 🙃

Before this, running parallel Claude Code agents required manual bash scripts, custom worktree management functions, and a dozen Medium tutorials explaining the setup. incident.io wrote an entire blog post about their homegrown tooling just to get multiple agents running without clobbering each other’s files. Developers were spending 30 minutes configuring worktree workflows before writing a single line of product code. Now it’s one flag. This tells you where the actual bottleneck in AI coding has been sitting. The models got smart enough to write production code months ago. The constraint was filesystem isolation. Two agents editing the same working directory creates race conditions, corrupted state, and merge nightmares that eat more time than the agents save. Faros AI found that teams with high AI adoption saw PR review time increase 91% because the overhead of managing parallel output overwhelmed the speed gains from generating it. The --worktree flag attacks that exact problem at the infrastructure layer. Each agent gets its own branch, its own directory, its own universe. No coordination overhead. No “git stash, git checkout, restart AI” loops that destroy context. What makes this interesting is what it does to the developer’s job description. The Pragmatic Engineer reported that senior engineers are becoming “naturals” at parallel agent workflows because the skillset maps directly to what they already do: managing multiple workstreams, reviewing code across branches, and delegating tasks. The role shifts from “person who writes code” to “person who orchestrates 5 agents writing code simultaneously and picks the best output.” Cursor already ships 8-agent parallelism. Codex has background agents. The entire AI coding market is converging on the same realization: single-threaded development is dead, and the tools that reduce friction for multi-agent orchestration win. One CLI flag. That’s the whole moat.

MiniMax M2.5 vs Opus 4.6 Same prompt. M2.5 is open source and 20x cheaper. Which one do you prefer?

The "autistic jerk" vibe in Codex 5.3 is just a byproduct of its aggressive rollout strategy. OpenAI is clearly trading social calibration for raw reasoning throughput—it’s optimized to detect design smells early and kill them, even if it hurts your feelings. Claude 4.6 is the refined UX for collaborative engineering, but when you’re pushing the frontier of system-level logic, you want the model that treats your code like a cold-blooded kernel debugger. One gives you a warm feeling, the other gives you a 99% stress test pass rate. I’ll take the jerk for production.

10 days into 2026: - Terence Tao announces GPT & Aristotle solve Erdős problem autonomously - Linus Torvalds concedes vibe coding is better than hand-coding for his non-kernel project - DHH walks back “AI can’t code” from Lex podcast 6 months later An acceleration is coming the likes of which humanity has never experienced before

Type shit

Introducing shadcn/create – Build your own shadcn/ui Customize Everything. Pick your component library, icons, base color, theme, fonts and build something that doesn’t look like everything else. Now available for Next.js, Vite, TanStack Start and v0.

Some of my kids came to the conf 😁 Get your own at Ship AI Photo Booth!

@marclou Check out @corridorsecure who just joined our marketplace and they do security analyses that run before a Vercel deployment can be promoted to prod: vercel.com/marketplace/co…

there's so much you can do