Recent submissions

Comment · 8 days ago
^ this. If Microsoft says it, it's true. Who posts this stuff? Real issues in diagnosis after the first follow up question (microsoft doesn't talk about that).
Comment · 9 days ago
Comment · 10 days ago
Inevitably where the "AI buying things for you" marketing pitch was headed - anyone have dibs on the next marketing trend from hedge funds (so they can keep shell game going..)
Comment · 14 days ago
Anyone accountable for AI being deterministic (this is most of the bay) - am curious how they incorporated the movie into the BS they shill (if they do).
Comment · 18 days ago
The bar @ OAI is surprisingly low (watch a few minutes of their video presentations) - I've concluded it has something to do w how their recruiters define 'AI Native' (who assign their own meaning to meaninglessness of it), resulting in higher aggregate brain atrophy (hard to ignore once you notice it)
Comment · 20 days ago
No “human bottleneck”. A probabilistic technology was never able to automate (this has been a marketing lie for a few years now, old news)
Comment · 20 days ago
Curious where it’s being documented - this is a fascinating study (who knows how long time period to measure its impact will last) - do you have links?
Comment · 1 month ago
Comment · 3 months ago
Comment · 3 months ago
Comment · 3 months ago
Cliche topic - from a few years ago (the "RAG is dead" vs "All You Need Is Advanced RAG" BS - it came in waves and cycles, spread by bots on social media networks).

"Pruning RAG Context" is trying to recycle the old stuff (again), presuming the reader is naive (implies kapa.ai is not going anywhere). The current cycles were "openclaw" (I think that died), now we are on "harnesses" - when that dies the paid social media bots will give you something else. Shell game.

Just declare / define dictionary as a variable in your prompt to carry forward (when you decide to continue using LLMs for certain things). Also either summarize or truncate history. 3-4 year old concept. Not a big thing.

Comment · 3 months ago
Comment · 4 months ago
Great viz; the original paper wasn't peer reviewed; it might be great but I've learned its a waste of time to read those in current times (sorry and take this as one data point that suggests they should have done that).

That said, I've found FAISS great for certain use cases; wanted to say thx for surfacing - its not updated to work with most packages these days outside of faiss-cpu - curious why Meta dropped its maintenance; was it due to its slower speed or otherwise priorities?

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton