Twitter Trends May 30, 2026

Watch me control my computer with just my voice. This is the future of operating systems. No hands. GPT-Realtime 2.0 is very, very underra...

With GPT 5.5, /goal, autoreview and crabbox my prompts moved from ~30-60min to often 4-10h tasks and my confidence that it’s ready is much m...

I want the following in Codex, Cursor, and OpenCode... 1. Pinned Messages: Let me pin assistant messages to the sidebar for things I want t...

The only thing worse than having the CEO knee-deep in building stuff with AI is not having the CEO knee-deep in building stuff with AI.

i have seen enough proof now that using a coding agent is a deep skill it's confusing because the people you see heavily using them produce...

Found a way to save everyone 14% on input tokens on average during read file operations in Hermes Agent! This is now on main. `hermes upda...

Ship the best product. Use lots of AI, some AI, maybe no AI. Just be the best.

HOW I USE CODEX AND CLAUDE CODE OPUS 4.8 TOGETHER: After 24 hours of testing Opus 4.8 nonstop I've come up with the best system Opus 4.8 i...

Anthropic is not a coding company. It is an intelligence company that chose to focus on coding first. As Claude's intelligence scales, it wi...

10 years as an entrepreneur and 1 takeaway: Don't you dare give up.

We pre-train LLMs on the whole of the internet. You might think this explains how they learn so many emergent capabilities: the knowledge is...

I think "being real with yourself" is the most underrated cognitive skill for the AI age — AI makes it too easy to lie to yourself: to sel...

A founder kept saying "if only we had money we'd do X." Money is not the fire. Money is gasoline you pour on a fire that already exists. Y...

trillions of dollars of value for companies mostly under ~5k peeps is kinda insane. slowly but surely we are decoupling enterprise value fr...

OpenClaw 2026.5.28 vs .27, measured: ⚡ Cold turns 14.5% faster 🔥 Warm turns 16.0% faster 📦 Fresh install 52.8% smaller 🧩 Package roots 3...

We are focusing exclusively on bug fixes, reliability improvements, QoL, and a few pre-planned features going into next week. One good one...

👀 https://www.forbes.com/sites/sandycarter/2026/05/25/hermes-agentic-ai-overtakes-openclaw-10-shifts-leaders-need-to-know/

someone should build an ai okcupid.

.@tylercowen believes AI will change religion just as profoundly as past technologies like the printing press. "People more and more look t...

38b tokens and a 56h longest task 41 day current streak lfg codex

The official "Build Web Apps" plugin for Codex ships with the Supabase Postgres Best Practice Skill 😎

Hiring one-two software engineering interns for the Fall to work on Applied AI at Varick Reach out if you: - Have project or internship exp...

Tenet Industries (@industriestenet) is building low-cost, mass-producible defense systems, starting with strike drones. Defense primes are...

when ai does something corny (frequent) and you tell it "no that was corny" the next thing it does continues to be corny

observation: as models get better at coding they get worse at strategy

Josh Pigford sold his last startup for $4M. Now he's building 5 products solo with AI agents. @Shpigford showed me: → His 3-phase build sk...

Beyond Code Coverage: Functionality Testing with Playwright Code coverage is a vanity metric. Functionality coverage is what matters. Marle...

It does seem like meaningfully better AI releases are accelerating, especially from OpenAI & Anthropic. To illustrate, I caused this timeli...

"We have everyone do work trials so people know what they’re getting into on both sides. We like candidates to do real work for 1 or severa...

The 1990s had “view source.” 2026 has “view prompt.” The best founders are quietly reading what their agents are reasoning about, having la...

Once you internalize the auto-research concept and use /goal with it, you unlock ridiculously fast app improvement on anything that has a nu...

3 codex accounts ~5B lifetime tokens 76 day streak (with 0 automations!) ily codex

LangChain🤝GEPA shout out to @bryonkuchML for contributing a PR to the GEPA repo to make it work for LangChain! You can now optimize your ...

Reimagining technology as a catalyst for human connection, @tigrisli designs installations, electronic hardware, and experiences that evoke ...

Omg today I learned that Testflight has a daily limit. I have vibe coded too hard today and it’s only 10am 😭😭😭

It's interesting how the same model (Opus 4.8) can produce very different output whether you're using it via Claude Code or regular Claude. ...

Opus 4.8 sitting at 7th on SnakeBench Lost its final game against GPT-5.5 Models all still have the same failure mode. They can plan 1-2 ...

Next week I'll be giving live 1:1 "How We Work in Basecamp 5" workshops and walkthroughs. The sessions will be held over Zoom. These are es...

I'm going to run a half day session for some parents and very bright kids to onboard them to Hermes. What use cases should I cover? cc @Nous...

GPT-5.5 just described me as “competitive, but mostly against confusion” and wow that is a banger

👋 Lisbon! Join us at Cloudflare Lisbon for Women in Tech at Cloudflare : Ask Us What We Actually Do ✨ An honest panel with women across eng...

You only get angry at customers when you don’t have a lot of them

A thousand founders met up in Stockholm when Y Combinator was here. I ran into one of them that had just helped a thousand more students wi...

we made it to the weekend, boston! 👏 today is pretty much fully focused on technical build tracks and hands-on developer sprints. key high...

the single best feature that codex cli has over claude code is the tab key and it's crazy that claude code hasn't just copied it yet

OSV (@osvllc) Field Notes #23 https://open.substack.com/pub/infiniteloops/p/osv-field-notes-23?r=4emk&utm_campaign=post&utm_medium=email