Show HN: Timberlogs – Drop-in structured logging for TypeScript
9 points
4
Show HN: BGP Scout – BGP Network Browser
(bgpscout.io)
10 points
5
Show HN: OpenWork – An open-source alternative to Claude Cowork
(github.com)
187 points
37
Show HN: Gambit, an open-source agent harness for building reliable AI agents
(github.com)
71 points
14
Show HN: Reversing YouTube’s “Most Replayed” Graph
(priyavr.at)
49 points
16
Show HN: TinyCity – A tiny city SIM for MicroPython (Thumby micro console)
(github.com)
128 points
22
Show HN: Tabstack – Browser infrastructure for AI agents (by Mozilla)
114 points
21
Show HN: A cross-platform toolkit to explore OS internals and capabilities
5 points
1
Show HN: Sparrow-1 – Audio-native model for human-level turn-taking without ASR
(www.tavus.io)
118 points
47
Show HN: The viral speed read at 900wpm app
(wordblip.com)
5 points
1
Load More Posts
Training large language models on narrow tasks can lead to broad misalignment
OP
by
thebeardisred
today at 6:17 AM
5 points
1 comments
www.nature.com
Comments
Loading comments...