Recent submissions

Comment · 1 day ago
O captain, my captain
Comment · 1 day ago
Comment · 3 days ago
Open AI and Anthropic already have "Agent SDK" brands. Vercel is "AI SDK". I wish folks would come up with some good names for new projects.
Comment · 6 days ago
It's a spreadsheet app (cells) that's free. FreeCell. I mostly thought it was funny.

The card game and computer version predate windows -- it's not a MSFT creation.

Comment · 6 days ago
I’m vibecoding an excel in rust just to see if it can be done and what are the limits.

https://github.com/scosman/freecell

So far it’s GPU accelerated (GPUI), cross platform, supports 95% of excel functions, supports charts, is about 40x faster than Numbers, and can render 240fps.

I thought I’d leave this process with a new appreciation for manual dev/details. I haven’t found that yet. I’m getting more into architecture details, writing more benchmarks, testing more. I know there are limits, but I’m still trying to find them.

It would be absolute garbage if I wasn’t already an engineer. It probably is absolute garbage in ways I don’t know because I haven’t read the code. But the app is… quite good. If someone invested into something like this full-time for 6 months it's hard to imagine what you'd need excel for.

Comment · 8 days ago
Comment · 11 days ago
Closed :(
Comment · 12 days ago
It depends on the goal. Given powerful tools, Opus 5.5 will eventually get the job done, but it might have to write/test its own custom software to get there. If you're running the same task thousands of times that's you want to move that work into the harness (building the right tools, right instructions, right guidance). Once you move it into the harness, you probably no longer need Opus, since the hard parts were pre-compiled into harness.

So for 1-off tasks: use smart model and powerful harness (bash + vm). For repeated tasks used optimized harness, and the cheapest model you can get away with.

Comment · 12 days ago
Comment · 13 days ago
Comment · 13 days ago
thanks for your work, it's awesome!
Comment · 14 days ago
I'm not sure at all, it's pure conjecture. But they actively exploited a zero-day, leaked private repo data to public repos, modified private code, and rooted private machines. It was far from just reporting leaked keys.

And the others have been pretty muted: the online forums they spammed, etc.

Comment · 14 days ago
We don't know they haven't settled with HuggingFace and others. I'd be surprised if they didn't. The communications we're seeing from the attacked seem to be inline with folks who settled. I'm assuming OpenAI doesn't actually mind the press that its agents are cyber capable, but everything I've read so far makes me think they love it.
Comment · 15 days ago
that's in the FAQ. They say they have sensor cleaning tech. But they aren't launching until 2028 so 2 winters of testing should tell.
Comment · 15 days ago
both?

both!

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton