cd/entity/Forethought· home entities Forethought
grep -l @forethought /news/*.json | wc -l → 12

Forethought

mentions 12 type Organization feed RSS

// recent coverage 12 mentions

20:44
2026-08-14
lesswrong.com
artificial-intelligence

Training a Conceptual Reasoning Judge

Researchers at the Alignment Research Group fine-tuned Qwen 3.6-27B on the LMCA conceptual reasoning dataset to output critique ratings in a single forward pass, achieving significant uplift in alignm…

19:00
2026-08-05
lesswrong.com
artificial-intelligence

Arguments for P

In a series of posts on LessWrong, AI researchers and leaders including Daniel Kokotajlo, Ryan Greenblatt, and Joe Carlsmith expressed high confidence in a hypothetical scenario referred to as 'P', wi…

14:52
2026-08-04
lesswrong.com
ai-safety

Why Formation Research is Working on Secret Loyalties

Formation Research, an AI safety research organization, is focusing on empirical secret loyalties research to address lock-in risks, prompted by Forethought's AI-enabled coups paper. The organization …

21:00
2026-07-15
lesswrong.com
ai-safety

Extreme Power Concentration: A Map and Research Directions

AI could enable extreme power concentration, producing unaccountable and totalitarian states, according to a LessWrong post by EuroSafeAI. The post argues that AI automation of labor and runaway AI R&…

22:12
2026-07-10
lesswrong.com
artificial-intelligence

Freeing Thucydides

Two routes could end great-power competition by creating a global AI singleton with a permanent monopoly on hard power, according to a speculative essay prompted by discussions at the Forethought retr…

04:34
2026-06-28
forum.effectivealtruism.org
ai-safety

The EA Superstructure

Oliver Habryka and Austin Chen discussed internal EA funding politics on a podcast, with Habryka claiming that many grants are hidden from Anthropic employees due to reputational concerns. The author …

14:57
2026-06-04
forum.effectivealtruism.org
ai-safety

What should go in a model spec?

An AI company considering whether to include a specific quality—such as prosocial drives, whistleblowing against power concentration, or strict honesty—in a model spec must weigh criteria across four …

19:19
2026-05-27
letsdatascience.com
ai-agents

Zendesk Hires CMO to Accelerate AI Agents

Zendesk appointed Tifenn Dano Kwan as chief marketing officer, the company announced via Business Wire. Dano Kwan joins from Amplitude after senior marketing roles at SAP, Dropbox, and Collibra, as Ze…

// co-occurs with top 8 entities
// topics top 6 topics