punsn__ retweeted
Introducing agent-desktop
agent-browser, for your whole computer
→ Computer Use for any coding agent
→ macOS, Windows and Linux
→ Runs in bg while you keep working
→ Agents use your computer in parallel, each with its own cursor
punsn__ retweeted
THE NEXT HERMES DESKTOP RELEASE IS GOING TO BE A BIG ONE.
Running Hermes on more than one machine is about to feel like one setup.
▸ Every gateway you've registered connects at launch and stays connected
▸ If one drops, it gets redialed automatically
▸ Switching is instant. No "Switch to This device?" prompt, no blank session list
▸ A gateway that was offline at launch shows its sessions about 30 seconds after it's back
Look for it in the next release, expected later this week.
And it's just the start. More UX and design work is lined up right behind it.

ALT Infographic: Many machines. One setup. Hermes Desktop connected to several gateways, with one redialing. Every registered gateway connects at launch and stays connected, drops get redialed automatically, switching is instant with no "Switch to This device?" prompt or blank session list, and an offline gateway shows its sessions about 30 seconds after it's back. Look for it in the next release, expected later this week. @HermesWatcher
punsn__ retweeted
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
punsn__ retweeted
MIT ทำ DevOpsใหม่ที่ผสม Coding Assistant AI เข้าไป โดยก่อนจะเข้า plan mode ให้ใช้ LM ถามก่อนว่าคนเขียนต้องการอะไร ตอบไปมาจนมันเข้าใจ เพราะปกติคนจะโยน code ให้ AI มันไปนั่งเดา ซี่งเปลือง token มาก พอจบ plan mode ก็แบ่ง subagents รับงานตามกระบวนการ DevOps ที่ถูกต้อง ซึ่ง DevOps framework ตัวนี้ ได้รับ Git vote ตอนนี้เข้าไปถึง 50K แล้ว
🚨 Holy shit...A developer on GitHub just built a full development methodology for AI coding agents and it has 40.9K stars on GitHub.
It's called Superpowers, and it completely changes how your AI agent writes code.
Right now, most people fire up Claude Code or Codex and just… let it go. The agent guesses what you want, writes code before understanding the problem, skips tests, and produces spaghetti you have to babysit.
Superpowers fixes all of that.
Here's what happens when you install it:
→ Before writing a single line, the agent stops and brainstorms with you. It asks what you're actually trying to build, refines the spec through questions, and shows it to you in chunks short enough to read.
→ Once you approve the design, it creates an implementation plan so detailed that "an enthusiastic junior engineer with poor taste and no judgement" could follow it.
→ Then it launches subagent-driven development. Fresh subagents per task. Two-stage code review after each one (spec compliance, then code quality). The agent can run autonomously for hours without deviating from your plan.
→ It enforces true test-driven development. Write failing test → watch it fail → write minimal code → watch it pass → commit. It literally deletes code written before tests.
→ When tasks are done, it verifies everything, presents options (merge, PR, keep, discard), and cleans up.
The philosophy is brutal: systematic over ad-hoc. Evidence over claims. Complexity reduction. Verify before declaring success.
Works with Claude Code (plugin install), Codex, and OpenCode.
This isn't a prompt template. It's an entire operating system for how AI agents should build software.
100% Opensource. MIT License.
punsn__ retweeted
Indian developer reverse engineered the protocol that AirPods use to communicate with Apple devices and implemented those features on Android (and Linux) |
punsn__ retweeted
Announcing Together Chat!
Use DeepSeek R1 & other top open source models to do web search, coding, image generation, & image analysis.
Available today for free!
punsn__ retweeted
I believe that a misunderstanding of the formula for GRPO is currently spreading, because people don't actually look at formulas in detail. can someone please check my sanity? because surely someone else would have noticed, if I was right.
in the deepseek-r1 paper, square brackets are used to denote what we take the expectation over (i.e. the domain of the expectation), which is of course highly unusual and confusing, as we usually put into square brackets what we take the expectation of. this leads many people to falsely believe that we have the expectation of q ~ P(Q) and {o_i}^G ~ \pi(O|q) times the 1 / G * sum term.
on the off-chance that I am indeed not wrong in my understanding, I believe that it would be beneficial for the sake of clarity if the authors would change the formula to fit the standard convention by turning that which is currently in the square brackets into a subscript of the expectation and putting the other term into square brackets.




































