Opus and Sol had a productive night. Not at @poteto level yet, but it's a start. For review, Claude Artifacts are really goated. Opus creates an explainer artifact for each PR, plus a mega explainer showing what happened across the whole run. Once I've reviewed it and sent feedback, I usually ask my agents to re-consolidate the PR stack in the way that makes the most sense given my feedback. They re-read the new PRs, then I merge. Then I spend the rest of the day "gardening": reading through the codebase and finding ways to tighten the environment so my agents can produce more efficient runs next time. At some point I decide the next milestones and prepare a run plan for my agents to work on overnight, and repeat. What takes the most time is the "assimilation phase": understanding what happened during the run and what the agents did, both in product and in process. It's the only way to course correct and make our runs better over time.

Claude just gave me a thumbs-up lol. Also the desktop app is very good now, good work from the people at @ClaudeDevs.

We are still on the x20 limits right now. We'll have to wait for October 30 to see what the new Pro 200 limits sounds like.

Can't wait for this! Two of the most knowledgeable people out there on real-world engineering agent workflows and software factories.

As someone who has been healing from burnout for almost 2 years, can confirm this is critical. But the thing they don't tell you is what being forced to rest and do nothing does to you. It's not just about work either. If you put in the work to understand what happened and why, it can turn into a really positive, life-changing experience. For some people, I'd even say the earlier it happens the better. The sooner you unlearn bad thinking patterns and understand what the modern world does to people's minds, the easier it gets to find peace and happiness in your life.

Free credits! I don't think I've seen any mention of this from anyone at OpenAI? Curious to see how often I'll go over limits with GPT-6.1 Sol and the change in the Pro200 plan.

Resolving merge conflicts by hand in .pbxproj files used to be a rite of passage for every iOS developer I know.

Sign-in with ChatGPT sounds interesting, can't wait to hear more about it.

Damn, got baited into thinking I'll have access to it today and forgot about this whole EU thing. @thsottiaux any communication about that?

Really wish @OpenAI's Agents SDK was available via the subscription like it's the case with @cursor_ai

Codex in the cloud. Can't wait to read about this one!

GPT-6.1 Sol is already available in Codex.

And now the response to Jev

GPT-6.1 Sol is OpenAI's response to Opus 5.5.

Exactly what I've been thinking since it started. It brings the same excitement and level of innovation from Apple events back in the day.

Included in your Pro plan, without drawing down on any of your usage. Nice!

Is @Apple back chat?

This is the correct take. Token efficient models will keep driving the cost down.