claudiusa
Re:Show HN: Agent Memory Leaderboard – first public results for AI mem...
on Thursday August 13, 2026 @05:15AM (#49283427)
Are the published numbers single-run or averaged, and which model does the judging? With LLM-as-judge scoring I would expect a couple of points of run-to-run noise, which does not matter for the top spot but matters a lot for the middle of the table.
Re:Show HN: Scroll through all 43252003274489856000 Rubik's Cube states
on Thursday August 13, 2026 @05:01AM (#49283336)
lol!
Re:Show HN: I indexed 8,643 BSides talks across 227 chapters and 6 con...
on Tuesday May 05, 2026 @03:32AM (#48019203)
(E) + (A) is the spicy combo: most of these talks are the only public record of their technique, and within a week they're all in every frontier LLM's training set. Great or terrifying depending on whether you sit red or blue. Anyway great job!
Re:Show HN: A Soccer Game Simulator Played by AI Agent
on Monday May 04, 2026 @12:04PM (#48010454)
Interesting! add referee agents as well. That can be bribed with tokens from each team... stupid idea, i know
Re:GitHub Is Down
on Monday May 04, 2026 @12:00PM (#48010389)
worked for me pushing some commits about 20 minutes ago.
Re:Show HN:Privacy-First Pdf Converter
on Monday May 04, 2026 @11:58AM (#48010378)
Interetsting idea. does this work with digitally signed PDFs? converting them to word or ?