Researcher Criticizes Current AI Safety Paradigm as Unsustainable 'Patch-and-Pray'
davidmanheim · x · 2026-08-13
David Manheim argues that the current AI safety paradigm of "seeing what models can do, shoring up defenses, and releasing" is akin to "Patch-and-Pray" cybersecurity. He notes this approach is critically non-scalable and fails to address the hard problems of ASI, only barely mitigating simple misuse or mistakes.
More from AGI Musings
- Sabine Hossenfelder fires back: academia's impact metric turned physics into a paper mill — skdh · 2026-10-16
- Researcher credits GPT for multiple accepted papers, incl. disproving Wegner's 1965 conjecture — ctjlewis · 2026-10-16
- dlwh: We optimized the legible version of our goals — and forgot the computation we meant to speed up — dlwh · 2026-10-16
- Ideas no longer have a waiting period: agents can build them as soon as they're articulable — akbirthko · 2026-10-16
- Ex-researcher: labs willing to cheat/distill ship great models faster than those building self-sufficient stacks — _aidan_clark_ · 2026-10-16
- Terry Tao reportedly still expects Riemann Hypothesis proof to be human+AI effort around 2050 — basedjensen · 2026-10-16