at://
/
app.bsky.feed.post
/
3lqn4hfdvzm27
sign in
All
4
Record
2
Post
1
PostEmbed
1
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
Even the best LLMs struggle to execute scientific workflows. SOTA models including Gemini 2.5 Pro, Claude Opus 4, o3-mini and QwQ crash 30-60% of the time and only produce visualizations without error in less than 16% of the cases.
Jun 2, 2025
Sebastian Joseph
