Recent submissions

Comment · 11 days ago
Spending time upfront designing is sound advice for any software engineer. LLMs can also save time here as well, if you're disciplined enough to not proceed until the design is polished.
Comment · 11 days ago
Given how many security vulnerabilities SOTA models are able to catch in software we've considered some of the most mature ever written, they can most certainly be more reliable in certain contexts and when used certain ways.
Comment · 11 days ago
I think an isolated and ambiguous sentence like the one you provided with zero surrounding context is perhaps a bad example. English can be very ambiguous. It is also possible to write unambiguous English, as far as deciphering intention is concerned. I think LLMs have shown us just how far English can go as a medium to get quite good results. And as others mention, there are other tools, like compiled programming languages and static analysis tools and unit tests, that can do more of the heavy lifting on our behalf.
Comment · 11 days ago
Nice work. I unfortunately wouldn't be able to use it for programming because I find the parenthesis and square bracket look too similar, and it would definitely increase extraneous cognitive load.
Comment · 11 days ago
I think the OP was talking about robotics specifically and not tasks like the one you described. Nobody can argue that for tasks like your binder replacement cost savings are enormous.
Comment · 12 days ago
I agree with this to a large extent. This new technology is lowering the barrier to meaningfully work with existing tools. It's increasing the magnitude of jostling that may very well bump us out of a local maximum sooner than before.
Comment · 16 days ago
I would argue that all of the problems we have to solve are novel and tricky. The rest we've already solved but constantly reinvent (not novel) or already solved and just need to piece together like Legos (not tricky).
Comment · 18 days ago
Forgive my ignorance, since I am only superficially knowledgeable about this, but how are you certain that it "completely forgot" as opposed to the knowledge still being encoded but 800 inferences was not enough to probabilistically trigger it? Like hunting down a race condition that happens rarely enough that it may not surface in 800 runs of the program.
Comment · 18 days ago
I'm also working on an educational game project in C++ compiled to WebAssembly with Emscripten. Absolutely awesome to work with.
Comment · 22 days ago
Teaching Assistant
Comment · 1 month ago
We have the power to change this
Comment · 1 month ago
Out of curiosity, what definition of "intelligence" are you using when you say that an LLM doesn't have it?
Comment · 1 month ago
Gorgeous! You're an amazing photographer.
Comment · 1 month ago
Wow. Thank you for offering a portal to this other world through your beautiful writing.
Comment · 1 month ago
or treat the triangles as if they were part of a larger white flag?

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton