A playbook for building apps: - find a problem you have - open a LLM provider (like ChatGPT, Claude, Gemini, Grok, etc) - chat about your problem and get help from there - iterate - at some point, it will become harder for the LLM to manage the context and the memory - then it's time to ask the LLM to give you a prompt that will give you all the info from that chat to help you turn that chat into an app (like an iOS app, MacOS app, etc) - iterate until you have a stable version - go distribute it as there will be more people to have that problem as well Right now I'm doing this. Making an iOS app using Devin for my GYM sessions. Now it is tailored to my needs, but I'm pretty sure it can be used by others that need my structure.

The best way to spend your Saturday evening is to review what's new on pstack lol

My hot take from chatting to @poteto is that we should use MORE abstractions in the AI age You can use them (combined with harsh lint rules) to reduce the design space available to the agent and constrain them only to good decisions. Combined with the fact that high-leverage abstractions let you do more with less code - so, more token efficient. Plus, unwinding the damage from a bad abstraction is much cheaper with agents. This runs counter to a lot of folks thinking that agents just want to read the raw code. They can, but they're not maximally efficient that way. Be braver! Design abstractions.

i love using devin

Used to watch these tutorials..

tried something weird today gave Devin access to my Screen Studio license and asked it to make me a demo it was… ok but Screen Studio has no docs for agents so it kinda flies blind and you end up guiding the clicks anyway cool idea, missing piece still

I found a life hack “Freely you have received freely give”

This is so exciting! I give all the tools I use to my agent to use them. Crazy times!!!

This is how you should prompt your agent

cute

One of them and I love the product. So well done.

Is the Slack app still in Beta for Mac users??

GPT-6.1 Sol is now available in Devin. On FrontierCode 1.1, GPT-6.1 Sol scores 60.4%, in line with GPT-6 Sol (60.7%), but at a fraction of the cost. At medium reasoning effort, it costs $0.31 per task, 81% less than GPT-6 Sol at max effort.

I'm at OpenAI's DevDay event in San Francisco today - as I have for the past three DevDay events, I'm running a live blog where I'll be posting updates during the keynote, which starts in five minutes simonwillison.net/2026/Sep/2…

friendship with sol has ended. opus 5.5 is new best friend.

My dentist has the best studio

Winter is coming and I'm prepared with my Omarchy machine

Sonnet 5.5 now in Devin ⚡