Viewing profile — extr

yeah it's true, you do have to guide them. i find that the key is you have to know what's possible. you have to have the instinct for "this really shouldn't be so difficult". my ju…

$80 is definitely low now that I look at my numbers. but not OOMs low, it's closer to like $200 on heavy days. i don't know how you're doing $3k/day, that's wild. i'm pretty aggres…

Yes lol. Of all things people are getting on me for it's the number of LoC x Years In Business of this startup. I don't fucking know, I didn't start the company and I wasn't here f…

> "unguided" means "I typed a prompt into claude code and waited yolo" Yes, this is literally what that means.

This is a great point and I agree. My own productivity varies based on what part of the codebase I'm working on. If it's "been in there before" and I know the right questions to as…

It's a fair point, it's not truly unlimited and I do wonder how that would change my workflow. I can definitely imagine if I was inside Anthropic or OAI with unlimited "fast" token…

No, actually. The point is to build a profitable business.

> unguided LLM usage Why aren't you guiding your LLM usage? Is that what I said - to spam it and not guide anything? Or to have a careful workflow where you agree on design and max…

How is this not true? Taking a Senior SWE @ ~$200K, even just the base salary cost / 2080 working hours is $100/hr. Fully loaded employer cost + accounting for non-coding time gets…

Yes 100%. This morning I casually prompted Codex to drive the browser to complete extensive performance testing in-situ that would have literally been weeks of work before. Probabl…

Have you worked at many startups?

This was more true a few months ago but Fable has improved the situation considerably. Also just remember - minimalist code looks and feels great but customers do not read your cod…

Disagree. I operate this way inside a multi-million line legacy codebase.

Keep the decision-making and execution separate. Use the high IQ models to chat about the design and make them drive subagents to do the actual work. "Chat" style threads are actua…

Performance is better than ever. It's never been more practical to set up wildly complex synthetic test environments and measure perf wins. Plus the models will find every possible…

I would be really curious to hear from devs at Databricks what the experience of development is like internally. I work at a small startup with essentially unlimited AI spend budge…

I don't really care if it was made by AI or smeared onto the keyboard by a monkey. It was effective in it's job and communicated clearly.

Well made website IMO. Gets to the point with plenty of easy-to-understand evidence and calls to action.

Seems pretty reasonable.

I think DeepSWE is flawed in a different way: the tasks look like someone took a bunch of big highly technical PRs they found really well done, and inverted it into specs for agent…

[Future voice]

I'm skeptical any of that matters at all if at some point AI is perceived by the government to be a true existential risk to public welfare.

I don't know that I want to stop such a thing. It's good that nerve gas is banned. I don't want random people having access to easy-to-follow instructions to make COVID-29.

They are not going to let open weights models with zero restrictions exist dude. They will be regulated like guns, or probably closer to nerve gas or enriched uranium.

I think they were totally correct in spirit. But RE: details about them giving access to an SK corp with possible Chinese ties. Of course that raises eyebrows in the USG, justifiab…