First screen, captured . Open the video.
Captured . Click for the whole screenshot.
142 points by gmays | 65 comments
Blog post framing LLM reasoning as pathfinding in token space, explaining how RL with verifiable rewards maximizes success probability and why chains of thought may be unfaithful.
5 points by aaronbrethorst | 0 comments
Blog post by Aaron Brethorst arguing that prompting an AI well is essentially programming, explaining why engineers get more value from LLMs than non-programmers.
259 points by benzguo | 63 comments
49 points by ibobev | 21 comments
A blog post arguing Pratt parsing can be treated as a black box, explaining the nud/led mindset and binding powers with examples from the author's C++ compiler.
15 points by rramadass | 1 comments
A simple landing page linking to a PDF titled "I Do Understand Relativity" by Douglas Ross of the University of Southampton.
98 points by jandeboevrie | 23 comments
Blog post by Sandor Dargo introducing the C++26 <debugging> header for programmatic breakpoints, replacing compiler-specific code like __debugbreak.
530 points by nkko | 135 comments
Project page for LegoGPT, a Carnegie Mellon research model that generates physically stable, buildable LEGO structures from text prompts, with paper, code, and demo links.
344 points by todsacerdoti | 56 comments
Blog post by David Anderson explaining what PID 0 is in Unix/Linux, why it is hidden from userspace, and its role in booting and idle scheduling.
347 points by georgehill | 79 comments
Homepage for Simon J.D. Prince's book Understanding Deep Learning (MIT Press, 2023), offering a free draft PDF of chapters 1-21 under a CC license.
665 points by quantumgarbage | 295 comments
Project page for a research paper on extracting hidden reasoning traces from proprietary LLM APIs, by authors from MATS, ELLIS, Max Planck and Tübingen.