Hacker Newsnew | past | comments | ask | show | jobs | submit | _cs2017_'s favoriteslogin
1.
Agent design is still hard (pocoo.org)
426 points by the_mitsuhiko 21 days ago | 258 comments
2.
The Continual Learning Problem (jessylin.com)
102 points by Bogdanp 49 days ago | 8 comments
3.
Kafka is Fast – I'll use Postgres (topicpartition.io)
561 points by enether 45 days ago | 401 comments
4.
BERT is just a single text diffusion step (nathan.rs)
455 points by nathan-barry 54 days ago | 110 comments
5.
SWE-Grep and SWE-Grep-Mini: RL for Fast Multi-Turn Context Retrieval (cognition.ai)
97 points by meetpateltech 58 days ago | 31 comments
6.
Writing an LLM from scratch, part 22 – training our LLM (gilesthomas.com)
254 points by gpjt 58 days ago | 10 comments
7.
Show HN: I invented a new generative model and got accepted to ICLR (discrete-distribution-networks.github.io)
656 points by diyer22 64 days ago | 91 comments
8.
A small number of samples can poison LLMs of any size (anthropic.com)
1202 points by meetpateltech 65 days ago | 439 comments
9.
Reasoning LLMs are wandering solution explorers (arxiv.org)
90 points by Surreal4434 64 days ago | 98 comments
10.
Building the heap: racking 30 petabytes of hard drives for pretraining (si.inc)
412 points by nee1r 73 days ago | 274 comments
11.
We reverse-engineered Flash Attention 4 (modal.com)
134 points by birdculture 77 days ago | 48 comments
12.
Claude’s memory architecture is the opposite of ChatGPT’s (shloked.com)
448 points by shloked 3 months ago | 236 comments
13.
Le Chat: Custom MCP Connectors, Memories (mistral.ai)
398 points by Anon84 3 months ago | 165 comments
14.
A PM's Guide to AI Agent Architecture (productcurious.com)
208 points by umangsehgal93 3 months ago | 62 comments
15.
Physics of badminton's new killer spin serve (arstechnica.com)
119 points by amichail 3 months ago | 16 comments
16.
Dispelling misconceptions about RLHF (aerial-toothpaste-34a.notion.site)
120 points by fpgaminer 3 months ago | 32 comments
17.
Diffusion language models are super data learners (jinjieni.notion.site)
218 points by babelfish 4 months ago | 16 comments
18.
My Lethal Trifecta talk at the Bay Area AI Security Meetup (simonwillison.net)
430 points by vismit2000 4 months ago | 115 comments
19.
How attention sinks keep language models stable (hanlab.mit.edu)
219 points by pr337h4m 4 months ago | 36 comments
20.
Gemini 2.5 Deep Think (blog.google)
461 points by meetpateltech 4 months ago | 249 comments
21.
The Math Is Haunted (overreacted.io)
409 points by danabramov 4 months ago | 194 comments
22.
Hierarchical Reasoning Model – 1k training samples SoTA reasoning v/s CoT (github.com/sapientinc)
26 points by dreamer7 4 months ago | 6 comments
23.
Hierarchical Reasoning Model (arxiv.org)
339 points by hansmayer 4 months ago | 106 comments
24.
Study mode (openai.com)
1130 points by meetpateltech 4 months ago | 805 comments
25.
What went wrong for Yahoo (homeip.net)
255 points by giuliomagnifico 4 months ago | 265 comments
26.
Major rule about cooking meat turns out to be wrong (seriouseats.com)
325 points by voxadam 4 months ago | 250 comments
27.
A conceptual overview of asyncio (github.com/anordin95)
149 points by anordin95 4 months ago | 30 comments
28.
LLM architecture comparison (sebastianraschka.com)
418 points by mdp2021 4 months ago | 24 comments
29.
Apple Intelligence Foundation Language Models Tech Report 2025 (machinelearning.apple.com)
242 points by 2bit 4 months ago | 204 comments
30.
To be a better programmer, write little proofs in your head (the-nerve-blog.ghost.io)
463 points by mprast 5 months ago | 167 comments

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: