Debunked: AI didn't invent a cancer vaccine overnight — it picks neoantigens
GaryMarcus · x · 2026-08-20
Viral claims that "AI suddenly discovered a cancer vaccine" are engagement bait. Moderna and Merck reported positive Phase 3 results for Intismeran plus Keytruda in 1,137 post-surgery melanoma patients — a real and important result.
But the vaccine entered human trials in 2017, and AI/bioinformatics was used to analyze mutations and select up to 34 neoantigens per patient for the personalized treatment — it did not independently invent the vaccine or cure cancer. Full Phase 3 numbers are unreleased, overall survival is unknown, the treatment is unapproved, and it was tested with Keytruda, not alone. BioNTech, Roche, NEC, Transgene and Evaxion have used similar ML approaches for years.
More from Research
- Dev critiques compiling fast programs into slow neural nets: fun, but not useful — ctjlewis · 2026-10-16
- New paper uses revealed-preference methods to unpack why AI agents cooperate — brwilder · 2026-10-16
- Logit lens on a Beat Saber finetune reveals it reuses language grammar circuits — ctjlewis · 2026-10-16
- 128×128 record stands: how intermediate-work experiments foreshadowed reasoning models — ctjlewis · 2026-10-16
- TeamFusion: preference-based AI proxies debate to preserve minority views in team decisions — burkov · 2026-10-16
- MIT's C-GMT gives humanoid robots whole-body compliance without sacrificing motion tracking — MIT_CSAIL · 2026-10-16