o4-mini
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
2recommend
2warn against
Nov 3, 2025first mention
Mar 17, 2026latest mention
Why people recommend it
“we again found it performed even better with x00k tokens”
“o4 mini was pretty good too”
Caveats and dissent
Often compared with
Threads where it came up
- ZK-STARK proofs made easy so you can prove claims without exposing data 1 mention
- Ask HN: Read‑only LLM tool for email triage and knowledge extraction? 1 mention
- GPT‑5.3 Instant 1 mention
- Gemini 3.1 Pro 1 mention
- Don't fall into the anti-AI hype 1 mention
- OpenAI signs $38B cloud computing deal with Amazon 1 mention
Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 6
“Juno (o4-mini-based AI oracle)”
“o3, 04-mini (crappy agentic models, BUT, that is okay”
“they were benchmaxxed so hard on math and science”
“o4-mini had previously convinced me wasn't tractable”
“we again found it performed even better with x00k tokens”
“o4 mini was pretty good too”