Astra and Opus checked his new technique, found the earlier work and ran the experiments
Handed code, data and a writeup to Astra and Opus 5.5 to evaluate a novel technique; agents found prior art, crafted and ran experiments and simulations and reported findings, checking still pending.
This only partly worked. Read what happened before you try it.
How it works
- He hands over code, data and a writeup
- The agents find the prior art
- Craft and run experiments and simulations
- Report the findings for checking
Why it’s worth knowing
They did not just read about it, they ran it.
Where it’s from
Summarized from a public post on news.ycombinator.com. See the original ↗