tdubey · HN

DWS A LLM Generated, "Drudge Report" style news site

apoorvumang · HN

TokenPath – token-level citations for LLM output, read from attention

@RahimNathwani · X

Not a direct answer but the guys at Exercism (non-profit that publishes really good and free programming language self-study courses) recently launched a separate site to teach junior programmers both vibe coding and software engineering fundamentals.

fristovic · HN

She watched me look at model rankings and asked what do the numbers mean... I literally had no good way of explaining it to her so I just came up with something that is approximately in the same ballpark as some of the benchmarks out there lol

@Galliard232634 · X

Come study with me on

niklio · HN

You write 8 text completions and open models score how predictable each word was too them. Predictable => clanker. You can share results with your friends. The scoring checks every word you write against the model's logprobs. Right now I'm using Llama3.1, Deepseek v3 and Qwen3 to keep costs low. I tried to calibrate it so other models (chatgpt/claude) score 100% and interesting human responses score in the 10-30% range. Totally free, no signup

samcymbaluk · HN

Axiom toolkit – Make your ideas precise enough to be proven wrong

@nilsvb · X

Just launched Lovelisti after a week of vibe coding: add one thing you love and tell me who you find. Here is my list :

@PraveenJangid99 · X

Multi Agent Discussion Rooms ;Mad World

@that80zguy · X

Check out what I just built with Lovable!

@WWolfson97 · X

@EsaiePelinyn · X

Check out what I just built with Lovable!