Mollick: Astra's non-p-hacked papers are amazing, but research taste is the hard part
emollick · x · 2026-09-04
Ethan Mollick expands on his Astra experiment: on one hand, getting accurate, non-p-hacked original research papers in under a couple of hours each is remarkable; on the other, the results weren't slop — they just weren't interesting.
His conclusion: even with prompts, solving for research taste remains a hard problem for AIs.
Related event: Astra Writes Flawless Papers but Lacks Research Taste, Mollick Finds(3 posts)→
More from AGI Musings
- Three reasons AI is not conscious and may never be, per Nature essay — anilkseth · 2026-10-21
- Everything in AI is downstream of a global status graph, says founder — gabriel1 · 2026-10-21
- Attention decays fast: breakout moments must recur every 6-12 months — gabriel1 · 2026-10-21
- Mathematician Daniel Litt concedes his AI bet, but says AI won't solve math — ziv_ravid · 2026-10-21
- AI SaaS monetization is cooked: consumers small, enterprises pay $20/month — menhguin · 2026-10-21
- Tim Dettmers: Academia is about to have a renaissance — the best AI work of the next decade happens in university labs — StasBekman · 2026-10-21