juan

@dexhorthy maybe we should see harnesses the same way we see UIs. llms as users, getting better outcomes from one interface than another.

this guy gets it

@samuelcolvin Mastra!

TypeScript people - I have a question: What's the best (least bad, most trendy) Agent Framework right now? Vercel AI, Mastra, Langpain-js - any other popular options? I mean for general applications (e.g. not coding agents). Do you even use a framework, or pretend you don't need one and let the coding agent one-shot a slop micro-framework each time?

@paulg beautiful :)

View of Stockholm.

@allisonology any particular subject/matter you would like to dwell on?

Hello will you be my mentor?

@dbreunig counterintuitive :) maybe the path forward is not copy/clone, but to question?

Frustration at GitHub and Claude outages and inconsistencies is a good argument against the idea that we’ll be able to vibe code everything we need.

@mastra next, build the company brain with mastra!

Your agents can now work with remote filesystems like S3, GCS, and Azure. Attach a provider to your agent's workspace and it can read, write, and manage remote files.

@ishaansehgal 🚀! next feature: webhook endpoints for actions?

you can finally rename your machines. and delete old ones too. sessions + workspaces vanish with them. no cleanup required

@paulg "I have never let schooling interfere with my education."

If you skip some or all of college to start a startup, it's on you to develop your mind the way college would have. And that's not something that happens by default in most startups.

@smthomas3 not even its cloned version 🙈

i can get an agent to rebuild a fully functional Microsoft Teams competitor in a weekend ...but no amount of agents or inference can configure Teams correctly for me

@raphaelschaad @ycombinator why wouldn’t these companies navigate NATO’s procurement?

MIT student asked a question earlier today that a lot of young founders are quietly wondering about: "Won’t the frontier labs just do everything?" Yes it's true that OAI/Ant are shipping at incredible pace, but it's quite easy to avoid their blast radius and build amazing startups: OpenAI is not going to build a cattle-herding drone, buy an old F-150 and drive from ranch to ranch like the founder of one of the fastest-growing YC W26 startups, Graze Mate. Anthropic is not going to integrate with dental insurance verification systems (Lance). Google is not going to navigate NATO procurement (Milliray). The value is in the last mile, not the model. Sales cycles require humans who understand the customer. And most importantly, the market is expanding, not shrinking: AI isn't cannibalizing the existing 1% software spend — it's unlocking the other 5-6% that was going to humans. That's a much bigger market for startups yet-to-be-founded than the one the labs are playing in. Now, what DOES seem risky? A thin UI layer on top of ChatGPT with no domain expertise; a general-purpose chatbot or assistant; or a product that gets obsolete when model capabilities improve. But — tools for specific industries; "full-stack" AI companies that actually are the service (AI law firm, AI accounting firm, AI uranium exploration company); or generally products where the customer doesn't want a tool but an outcome — are defensible ideas for startups.

@thomas_ag interested

If you're interested in testing the product let me know!

Yesterday's @ycombinator post from @t_blom (who I used to work for at @monzo) about the "company brain" didn't surprise me. We started @housecatinc last year, and are seeing something magical happen when you give agents access to your data and a computer they control.

@nayshins @0xblacklight rhetorical question 😂

@0xblacklight They've been asleep at the wheel?

feels like this should really be gitlab's moment, not sure why it's not are they asleep at the wheel?

@jvrsanch stripe.com/en-es

Best landing page that explains a complex product in simple terms?

@unclebobmartin Darth Bob! :) Love it!

@allisonology maybe

@0xjgv yeah

Do you think the moon feels pain when it gets cut in half

@swyx probably talking about different things. "code isn't cheap" when it lacks units of trust. "code is cheap" when it has units of trust. x.com/unclebobmartin…

fun to think about what the pm thinks vs what the engineer thinks in this scenario

@PhysInHistory en.wikipedia.org/wiki/Blind_men…

What makes people believe in flat earth theory? ✍️

@nikitabier honeypot 😂

One of the most important things that Elon taught me: People engaging in fraud are always the first and loudest to complain.