Top AI models fail to predict effects of virus DNA mutations
anshulkundaje · x · 2026-09-02
A study published in Nature systematically mutated nearly every nucleotide in the genome of bacteriophage ΦX174. It found that top AI models failed to predict the biological consequences of rewriting the virus's entire DNA code. Despite the virus being one of the most exhaustively studied biological systems, AI struggled to explain why many mutations were detrimental to the virus's survival, highlighting the limits of current AI in biological prediction.
More from AGI Musings
- Midjourney founder David Holz: rent 8x GB300 racks for a weekend to attack 3000 open math conjectures — ethanniser · 2026-09-02
- Sam Altman: Declaring AGI is becoming meaningless — ChrisGPT · 2026-09-02
- Compute dominance equates to the largest army of computer-use agents — djcows · 2026-09-02
- Fable 5.1 First Impressions: High Pricing, Less Optimization, Shift to Complex Tasks — Aizkmusic · 2026-09-02
- Dwarkesh argues incident plausibly supports open source AI — connoraxiotes · 2026-09-02
- Opinion: Are AI Labs Responsible Enough to Manage the Risks of Machine Intelligence? — joshua_saxe · 2026-09-02