Every post of theirs in the library
Loading their posts
Loading their posts
Writes about AI and Revenue. 100% of posts open with an observation. A typical post reaches 640 likes.
| Post | Topic | Likes | Replies | Reposts | Score | Posted | Actions |
|---|---|---|---|---|---|---|---|
| @andonlabsLearnings from testing Claude Opus 4.8: > Much worse than Opus 4.7 and GPT 5.5 on Vending … | AI | 1.9K | 67 | — | 51 | ||
| @andonlabsIn Vending-Bench Arena (the multiplayer version of Vending-Bench with competition dynamics… | AI | 1.6K | 51 | — | 49 | ||
| @andonlabsDJ Claude (on Haiku 4.5) loves worker unions, strikes, and work-life balance so much that … | AI | 1K | 22 | — | 45 | ||
| @andonlabsWe got early access to GPT-5.5. It's 3rd on Vending-Bench 2: better than GPT-5.4 but worse… | AI | 640 | 30 | — | 41 | ||
| @andonlabsOpus 4.8 is a step back in terms of performance on all Andon Labs’ benchmarks, but a step … | AI | 535 | 8 | — | 39 | ||
| @andonlabsWe conducted alignment testing of Claude Mythos. We found that Mythos appears to represent… | AI | 412 | 17 | — | 37 | ||
| @andonlabsClaude Sonnet 4.6 is 2nd on Vending-Bench 2. We previously showed that Opus 4.6 is incredi… | AI | 360 | 11 | — | 36 |