Sardonix

[Lydia Hallie ✨ @lydiahallie]

Just to avoid some confusion: auto-compact does summarize. When it runs, your whole conversation is replaced by a short summary. It doesn't keep the last 1M tokens around.

The ~967K is only when it runs on 1M models. Compacting itself is just one request that reads about as many tokens as the message you sent right before it, and it's mostly cache reads if your cache is still warm.

What @rohit3a found is that waiting until 967K means every message before that point uses a lot of tokens, because each one includes your whole conversation so far. Most of it is read from the cache, which is much cheaper (so this is usually fine as long as your cache is warm), but it still counts toward your usage and adds up as your conversation grows.

/autocompact 400k makes it summarize at 400K instead, so your messages never get that big.

[Joma Tech @jomatech]

Introducing ChatGPT for Dishwashing

GPT-6 achieves state-of-the-art results on dishwashing benchmarks for long-running jobs and difficult stains.

The Navier–Stokes Millennium Prize Problem is a $1 million challenge about whether the equations describing fluid motion can break down. In this video, I accidentally found a counter-example while trying to optimize my dishwasher. But in reality, OpenAI used 10,000 AI agents to find a proof in 88 hours: https://t.co/6HTwFfXnm1

Parody of the original GPT-6 Astra ad

@OpenAI #ChatGPT_Partner #chatgpt

Credits:

Written and Directed by Joma
Co-Writer - Henry Connor Coan IV @coan_henry
Production by Dauntlus Studios @dauntlus.studios
Producer/Co-Director - Marcus Liew @dauntlus
Camera Operator - Amos Lee @amoselijahlee
Art Director - Alethea Soo @aletheasoo
Art Assistant - Alicia Lim @aliciatkl_
Assistant Editor - GPT-6 Astra

Music: Tensions Run High by Soundridemusic
https://t.co/kBUsd2DK76

[Fiachra (Fiki) 马骏 @FiachraRM]

Bummer that Singapore is always the place for enterprise and gtm, and rarely a place where these big dogs will come to hire designers too.

We gotta do better to make this country a hot bed for more than just adoption, but design and development too

[ElevenLabs @ElevenLabs]

Hello Singapore.

We're hiring: https://t.co/kRReL8aoV2

[Claude @claudeai]

One more thing: we’re halving the price of cache reads on Claude Sonnet 5.5, to $0.10 per million tokens. That makes Sonnet 5.5 around 20% cheaper to run on most long-running work.

[Sardonix @Sardoniix_]

@alexmichaelio Luna, because the flowers are actually facing the camera which looks better

[Sardonix @Sardoniix_]

@xw33bttv Gonna utilise the 50% discount for one month of Claude Max, guess I'll find out for myself.

[Sardonix @Sardoniix_]

@derrickcchoi Memory usage, my work laptop only has 24GB and I'm running way too much stuff currently

[Sardonix @Sardoniix_]

@YourWaifu Then I'll just play the modded games instead of playing their brand new game?

[Sardonix @Sardoniix_]

@synthwavedd I've been using my ChatGPT sub aggressively and this doesn't even seem like it's remotely true

[Tibo @thsottiaux]

Day 1/

We have optimized the default speed to be ~50% faster across GPT-6 Astra and GPT-6.1 Sol through the subscription across all our products and partners using Sign in With ChatGPT (including OpenCode, Pi, Amp, Devin, ...).

No changes needed on your end and this should be felt within the next two hours.

[Richard Qi 🐟 @riccqi]

I built a native Metal renderer for Minecraft, and a shader that takes advantage of it: volumetric fog, dynamic lighting, water reflections and more.

It runs at 60fps at full retina resolution on a 5-year-old MacBook. I've always hated how laggy minecraft is with shaders, now it's solved.

Shoutout to Opus and Astra!

[Tibo @thsottiaux]

Over the next 28 days, each day we’ll either ship one thing that is a clear improvement and relevant for most codex/work users or ship a full reset. Let the improvements begin.

[Sardonix @Sardoniix_]

@dusangran @nbaschez There's codex exec too to run it headlessly, but it is pretty cool that you can trigger something on ChatGPT Work which is an always-on VM

[Nathan Baschez @nbaschez]

I have not seen near enough excitement about MCP Events https://t.co/tlWV1jyuxX

Right now, the only way most people's agents can wake up and do something is either A) cron, or B) you decide to message it

Event-driven triggers are a huge deal

[🥔🥔🥔 @argofowl]

everyone thinks codex computer use only works inside codex

it doesn't, it's a local mcp server in the chatgpt mac app and claude code can just call it, even headless with claude -p

same 8-task test: opus 5.5 on codex's engine got 6/8, codex itself got 6/8, cua driver got 3-4/8 at 4x the cost

cua's background mode on mac only goes through accessibility, so canvases and drags just don't land

codex's engine sends real clicks and drags to the app without touching my cursor

no hover though, and it's unofficial, so enjoy it until a chatgpt update breaks it

give this to your claude:

"Set up Codex's computer use as an MCP server for you on my Mac. Find the "cua_repl" entry in ~/.codex/plugins/cache/openai-bundled/unified-computer-use/<newest version>/.mcp.json and register it as a user MCP server called "codex-cu" with the same command, args and env. Then test it by using Calculator in the background to work out 12 × 12."

[Carnage @0xCarnagee]

SpaceXAI engineer, Lauren Tan:

"I shipped 1000 PRs last month. I'm at almost 800 already this month and we're on the 12th

I woke up today and 20 had already landed. I reviewed them on main, after the fact"

In a 1-hour session she walks the exact trust curve, from micromanaging one agent to auto-merging thousands of PRs a month

this is worth more than any $500 agentic engineering course

watch it today, then read how to build the same agent fleet in the article below ↓

[Sardonix @Sardoniix_]

Is it just me or is everyone missing the point on AI subs?

We are comparing token costs via API for each subscription, but it's a known fact that the same tasks require less tokens with ChatGPT models compared to Claude models.

[Sardonix @Sardoniix_]

@johnny_xx @_ak_111 I've used over $5000 in Opus 5.5 and roughly $500 in 6.1 Sol and I must say, so far I'm much more impressed with Sol's code.

[Sardonix @Sardoniix_]

@Codexresets_ Why does it say monthly usage limit in the image?