this if you really want to use a multi-agent setup, ask a side chat to audit your usage patterns. for example, having your main agent repeatedly message the same subagent is unnecessarily expensive. the context keeps growing and wastes input tokens even when cached if your main agent keeps asking a subagent to call a tool, the delegation is unnecessary. just let the main agent call the tool astra is smart. send it this tweet and ask it to audit things

I would like to clarify a few things: 1) The screenshot is my reaching out to Levent to coordinate our releases. I hope it’s clear from the message that we came in with the best possible intentions. 2) I never ever asked for Levent to be removed from authorship of his own work (as indicated by my text). I was surprised to learn during the call with Tristan that they had only solved Euler and not Navier-Stokes; after learning this we brainstormed possible paths forward. One option we discussed was that Tristan could be the lead author on a rewrite of OpenAI’s Navier-Stokes proof. It is in that context that I said “it would be simpler if Levent was not an Anthropic employee” because I felt it would be inappropriate for an Anthropic employee to author OpenAI’s work. Importantly it was admitted that internal Anthropic models had been used in their proof of Euler blowup; I therefore felt I could not consider Levent to be an independent academic. Another option I wanted to propose (but got cut short) is to offer access to our internal model so that they could try to finish their proof and bridge the gap between Euler and NS. Again I did not know how to navigate giving access to internal OpenAI IP to an Anthropic employee. 3) To reiterate it plainly: as my text clearly indicates, and as I said during our call, OpenAI's intention was to do everything possible to celebrate their mathematical achievements and the heroic efforts that they made on Euler. In the call I was immediately met with a litany of slander, including direct threats that if we were to announce Navier-Stokes he would immediately go to the press with a barrage of unfounded accusations. I refuted all these accusations but he replied “there is nothing you can do, I simply do not trust you”. I was confused why one would turn an incredible source for celebration (of their achievements!) into such bickering, which is when I said that I did not understand why one would risk their career [over unfounded accusations]. Genuinely, at that moment, I was trying to care for him and do a last ditch attempt to get a chance to give them all the credits that they deserve. I deeply apologize for this extremely poor choice of words, it is the opposite of what I was trying to convey. (I should say that I retracted them on the spot by the way.) 4) Overall, on a personal level, it was incredibly difficult to have these conversations. Levent refused to attend any of the meetings despite my repeated asking. As Sholto Douglas said, there will need to be coordination between Anthropic and OpenAI in the future; I felt I was doing a proxy negotiation with Anthropic while the Anthropic employee refused to directly participate.

A series of false and inflammatory allegations against me are currently circulating on social channels. To clarify, I came into the discussion following academic norms, and I'm disappointed that it has come to this. Anyone who knows me knows that academic standards are of the highest importance to me. Will have more to say tomorrow.

PSA: Astra can see your remaining usage % in Codex and keep it in mind while running a /goal so you can give it a budget in plain English like: “keep going until i’m down to 25%, or until you've solved it”

To calibrate you all on which reasoning effort to use for Astra, know that GPT-6 Astra on low performs better than GPT-5.6 Sol on high. If you were using high reasoning efforts with Sol and were happy, I suggest you move down to low or medium for Astra.

响鼓不用重锤 (a resonant drum needs only a light tap) is my favorite way to think about major model upgrades. Astra is really good at following instructions. please trim down your old skills, AGENTS.md, and custom instructions. i'd even recommend deleting everything and adding parts back only as needed. we've seen Astra follow old, overly prescriptive instructions so strictly that it ends up either constrained or being extra. you might need to give a junior engineer detailed instructions, but a principal engineer needs room to exercise judgment. share your high-level goal, define success clearly, and trust Astra to figure it out.

has chatgpt or codex ever saved you actual money? caught an incorrect invoice, found a billing mistake, canceled subscriptions, negotiated a bill, etc. what happened, how much did you save, and what was the workflow? reply or dm me. looking for real stories!

Siri sucks. So I made a way for Codex to act as my iPhone's voice assistant. Now Codex can read my screen, control apps, and take actions on my behalf – all in vanilla iOS 27.

In 2017 a viral news story claimed LLMs at Facebook went rogue, developed their own language, and had to be shut down. By now we're immune to such sensationalist headlines. The Hugging Face incident may seem like just another one. But it's not. I hope everyone watches this talk

some tips on 5.6 sol: 1. remove old slop. try disabling certain community skills and plugins, especially bundles with 20+ skills. think of 5.6 sol like someone who just grew from senior to staff or senior staff level: prescriptive guidance that used to help becomes micromanagement and makes the work worse. you can always add back what clearly helps. 2. turn on codex memory in settings. give codex feedback on what you like and don’t like, and ask it to remember. 3. you probably don’t need ultra. i do 95% of my work on sol high, sometimes use sol extra high, and have only used sol ultra for a handful of sessions. start with high and only move *up* when you’re not happy with the result.

3D pelican riding a tricycle, plus a pelican riding a pelican, demoed by @edbayes fun fact: no one read or edited the code, and no assets were uploaded. this was built entirely by giving 5.6-sol high simple text instructions like “set a goal to render this as accurately as you can”, “add a g-wagon”, and “can you add another ride: a pelican riding a pelican?”