Ben Gribbin

This is a shocking yearly price for analytics @DrizzleORM I want my money back.

Codex is the best coding model out there but utterly sucks at frontend ui. I haven't found a single model worth coding frontend ui with off the bat.

Literally one prompt on a sunday night on the pro plan 😂 @claudeai

@matteocollina Next 💀

Readers spotted that compression was not applied consistently in our React SSR benchmarks. TanStack Start had it disabled while the others had it on. We disabled compression everywhere and re-ran the tests. Here are the corrected results.

@thekitze This is the way

a 15" m5 macbook air might be the ideal laptop ... if it had a 120hz screen i don't need a powerful machine anymore i offloaded most of my dev stuff to mac studio... i just need to ssh from a beautiful thin and lightweight machine

@thsottiaux @dkundel In the codex app add an icon/indicator to the thread if it’s running a server from the terminal. Useful to know which threads in the sidebar are using the terminal etc.

Speed and front-end capabilities: we heard that loudly, and things are improving quickly, to the point where I think we are now highly competitive on speed, if not best-in-class. What else should we improve for Codex?

@tim_cook @grok and chance of Mac mini or Mac Studio m5 chips?

A big week ahead. It all starts Monday morning! #AppleLaunch

@LLMJunky Just realised you’re not discussing the Mac app sorry!

@LLMJunky We need an icon next to any thread which has the server running from the terminal so we know which one it is!

Codex update 0.105.0 is out! Despite the fairly pedestrian changelog, this one's a doosie. It's a laundry list of quality of life improvements across the board. - Wispr Voice dictation (hold space to talk) - Theme picker - Codex can prevent sleep on Linux & Windows (I just know there's a joke in there) - Customize Plan Mode reasoning - Many other fixes/updates There's also a complete overhaul to subagents: - New names for readability - Visual display overhaul (way cleaner) - Allow for multi-layered subagent depth (max_depth) - Custom multi-agent role definitions (custom subagents) - /agents now shows both agent names, agent roles, and "dead agents" for auditibility This is the largest single update of Codex I've ever seen! Absolutely massive if you love to use multi-agents. To turn on Voice Transcription, enable: [features] voice_transcription = true Does not work on Linux yet. Well done @OpenAIDevs 👏

@dvassallo Giving birth should be free

Last service for my car was $6K to have all fluids replaced, a timing belt, and an AC part. Almost all labor fees. I find that way more expensive than the hospital fees involved in delivering a human being into the world and caring for the mother for a couple of days.

$9K is really not that much considering 2-3 days of private hospital room and board, and all the medical staff assigned to you with zero notice.

@thsottiaux You got any good current tutorials on how to get the most out of it?

I’m constantly surprised by how much GPT-5.2-Codex can achieve, but it’s definitely a power user tool right now and requires investing yourself a bit. We will change that shortly and I think it will become a lot more accessible.

@aidenybai Whats up with the wierd domain you get redirected to on ami.dev ? ami-kitchen-sink.yummy-same.com/dashboard makes me nervous about continuing the onboarding

@aidenybai ami

We built the fastest coding agent for frontend This video is NOT sped up Comment "ami" for 100k free tokens

@JustJake Perfect timing 👍

Today we’re rolling out ‘railway dev’ Automatically spin up Railway projects locally, so you can move quickly, wherever you are We will handle the containers, local certs, etc railway dev -> railway.localhost

Here we go again

@AverageProMax @theo Tanstack uses react

As of 2 minutes ago, T3 Chat is no longer on Next.js 🫡

@DrizzleORM 💀

Should we rerun our benchmarks?

Use cloudflare

@benln Keen for this!

We're booking out a cafe on December 10th in London Grab coffee, Cursor credits, co-work, and meet the team Let me know if you'd like to come by

@thisismahmoud @Railway Legend.

@Railway Repo github.com/m-abdelwahab/u…

Pro tip: Use the private network when you can on @Railway. It's: • Faster • Cheaper (no egress fees) • More Secure Here's a demo comparing the latency of having an app query a database over the private network vs. the public internet use-the-private-network.up.railway.app