@kimmonismus your grandparents' PC is now an agent endpoint. we're so back
English
Clément Cochod
199 posts
holy: OpenAI is turning Codex into a control plane for your entire personal compute fleet.
Every Mac Mini, work desktop, devbox, and eventually browser session becomes an agent endpoint.
openai is cooking
🚨 AI News | TestingCatalog@testingcatalog
OPENAI 🔥: In the future, Codex will be able to control other desktop devices with the Codex installation. All your Mac Minis, your desktop station at work, or even your grandparents' old computers can form your own "Codex network". Along with the upcoming "Locked Use" setting, this feature will allow Codex to invoke Computer Use capabilities on other machines from your main device.
English
@thsottiaux shipping on saturdays is contagious apparently
English
I don't know why we ship on Saturdays now, but here are a bunch of nice improvements for Codex.
Didn't feel right to hold this back until Tuesday when it all makes it a lot more delightful to use.
OpenAI Developers@OpenAIDevs
We’re having way too much fun working through your feedback. (Please, keep it coming.) Keyboard shortcuts are now customizable. Set Codex up around how you actually work, then tweak shortcuts from settings instead of adapting to our defaults.
English
@OpenAIDevs cool now ship the agent that uses the shortcuts
English
We’re having way too much fun working through your feedback.
(Please, keep it coming.)
Keyboard shortcuts are now customizable.
Set Codex up around how you actually work, then tweak shortcuts from settings instead of adapting to our defaults.
English
English
The Codex Mac app rocks.
Visually I find it way easier to manage 10-15 tabs than Claude Code Mac or Terminal.
The battle rolls on! I was a hardcore Claude Code user and when @gregisenberg and @danshipper pushed me to try it I was skeptical.
Impressed.
A few pieces of feedback that would make Codex sing (CC: @sama and @fidjissimo):
1. Not having the AskQuestionTool available in work mode (only plan mode) is a travesty! Being able to quickly reply vs get a wall of 15 text based questions that I have to type answers to totally takes me out of my flow. (I updated my settings so that it always switched to plan mode whenever it needs my input, but many users won't do this).
2. I can't explain it, but something about the way it updates on its activity / loads / visually thinks, makes it feel slower.
3. Giving the sub-agents names (like human names) is actually distracting. I would prefer to be able to infer what the agent is/does based on its name (Legal Whiz, NextJS Master, etc).
4. If you could solve preference/environment syncing across multiple Macs, that would be incredible. Current Git-based solutions are very hacky and cause all sorts of errors. If I change my settings on my Mac Studio, I'd love it if it synced to my MacBook.
5. It seems weird that it can't control its own integrated browser and use it to click around sites (unless I'm missing something?)
Great work! Super impressed!
English
@gdb my computer is right there and i still can't stop using it
English
using codex from the ChatGPT app is such a freeing experience. makes you realize how tethered you normally are to your computer.
English
@thsottiaux reset my usage limits just to spend the weekend building ping pong apps
English
Codex usage limits have now been reset across all paid plans. Enjoy the weekend!
Tibo@thsottiaux
We found and fixed two issues that could explain this degradation of the capability of GPT-5.5 in Codex over the last ~ 48 hours. We are monitoring over the coming hours to fully confirm and I will reset usage limits this evening. Apologies and now is the time for /fast maxxing.
English
unpopular opinion: the best way to learn to build fast is to build something completely useless
shipped 2 ping pong apps today. no regrets
GIF
English
@gdb the AI that writes your bugs is now finding them too. full circle
English
@dreamsofcode_io 6,755 commits in 6 days and the vibe coder is unhappy. we're cooked
English
The code is so bad though.
Like the worst Rust code I’ve ever seen.
Honestly it’s so bad I’m thinking of fully hand writing code again.
WebDevCody@webdevcody
Bun rewrite from zig to rust in 6 days. 1,009,257 changes. 6,755 commits. all tests passing.
English
@garrytan layer 6 "epistemology" is doing more work than most entire RAG pipelines
English
What is GBrain? My open source project is a knowledge system, not RAG in a box.
It gives agents 8 layers that work together to improve memory in a way that makes your already smart OpenClaw or Hermes Agent feel clairvoyant about who you are.
Personal AI becomes possible.
English
the Codex app is in a category of its own. “agentic excel on mac” is an interesting description.
swyx 🇸🇬 AIE Singapore!@swyx
gotta say Codex is completely unrecognizable from 3 months ago. guys went extreme founder mode on this thing @gabrielchua was demoing this and i was like “you guys have agentic excel on mac”
English
@chamath friendster of AI is crazy coming from a guy who invested in Facebook
English
Anthropic needs to solve the computer/power problem or they will be the Friendster of the AI era.
I just ran a semi-complicated stock screening prompt on all four major AIs: Grok, Gemini, ChatGPT and Claude.
The first three returned comparable results. Claude refused to do the work.
Not the way to win guys…
English
@ChShersh 3,618,778 lines. the vibe coder has left the building
English
I asked AI to write me a function to parse a string in the YYYY-MM-DD format into std::chrono::year_month_day in C++
It produced a 100 LOC function. A hundred lines for a single utility function.
I had to guide it to use the standard library and it finally managed to write a one-liner.
AI really can spiral out of control if left unmonitored.
Roy Carrilho@RuiCarrilho5
this must have been so satisfying
English
@ctatedev built a programming language in 3 days and it works. AI really said "no more excuses"
English
I built Zero in 3 days.
I didn't expect it to compile.
I didn't expect it to mostly self-host.
I definitely didn't expect it to work at all.
Inspired partly by Bun's rewrite to Rust, Zero started as an experiment. Honestly, the project says more about where AI is today than it does about the language itself.
It took more than 3,000 agent tasks to get here, and it's still nowhere near ready for serious comparisons, benchmarks or evals.
But the goal is bigger than the current result.
The hope is to either create a new language with tooling designed for agents from the ground up, or take learnings and apply it back to existing languages and ecosystems.
The ideas are simple:
1. Make languages (and new versions) easy for agents to learn, adapt to and fix on the fly, even when not in the training data.
2. Build a standard library comprehensive enough that most projects don't need external dependencies.
3. Create a tight, fast development loop that even small models can reliably work with.
I've never wanted to create a programming language.
But after repeatedly running into the same problems, safe but slow builds, fast but unsafe builds, agents struggling with new languages and version changes, wanting faster builds, smaller bundles and better DX, I started wondering:
Could accelerated, agent-driven iteration produce a language and tooling stack designed around these constraints from the start?
So Zero was born.
Chris Tate@ctatedev
Introducing Zero The programming language for agents. I wanted a systems language that was faster, smaller, and easier for agents to use and repair. Explicit capabilities. JSON diagnostics. Typed safe fixes. Made for agents on day zero.
English
@sickdotdev used to be the left. Claude Code taught me the right.
English
@moshhamedani both are great but Claude Code wins on long context tasks. Codex wins on parallel agents. use both.
English
@gdb Codex finding your O(n²) loops so you don't have to cry in production
English
@GoshawkTrades 8,000 km of fiber just to run my side project's API calls
English
Jane Street just showed the inside of their AI training data center in Texas.
4,032 GPUs. 56 racks. 8,000 km of fiber. liquid cooling running through every server because air cooling can't handle the heat anymore.
but the part that got me was the origin story.
Ron Minsky, who co-heads their technology group. said their first compute cluster was literally six Dell boxes stacked on top of each other at the end of a desk row. they called it "the hive."
the trading systems sat out in the room with the traders because they wanted to be able to unplug them if something went wrong.
at one point, someone vacuuming the office unplugged a live trading system in the middle of the day.
from six Dell boxes and a vacuum cleaner incident to a liquid-cooled GPU data center processing trades in under 100 nanoseconds.
that's a 20-year arc.
English
@ycombinator @heyclicky 0 setup agent that spawns from a click. we're so early it's insane
English
Clicky is the simplest interface in the world to spawn agents.
It can see your screen, answer questions, make Notion docs, check your Google Calendar, create Linear tickets, and a whole lot more.
0 setup, built for consumers.
Try for free, download: @heyclicky.
English
@yegor256 every backend dev just had a mild panic attack reading this
English
RESTful APIs may be dead soon. Instead, web services may expose a single POST entry point for a prompt. Internally, an AI agent may decide how to interpret it and what to do with the data and the database.
English