The AI Alignment Forum

FEBRUARY 28, 2025

However, if we want to design a chess-playing AI that can invent completely new strategies and entirely outclass human chess players, then we must use something analogous to reward maximisation (together with either a search algorithm or an RL algorithm, or some other alternative to these).

Research 40

Research Learning Method Policy 40

Museum 2.0

SEPTEMBER 26, 2012

Deeper community relationships through focus groups or community advising committees can further help museums connect with issues relevant to their communities while also hold the museum accountable for their responses. This can be accomplished through a variety of feedback methods conducted both inside and outside the museum.

Museum 49

Museum Program Community Participatory 49

The AI Alignment Forum

FEBRUARY 7, 2025

Alternatives to adversarial training : Adversarial training (and the rest of todays best alignment techniques) have failed to create LLM agents that reliably avoid misaligned goals. Alternative approaches to mitigating AI risks These research areas lie outside the scope of the clusters above. Sheshadri et al., and Zeng et al.

Research 52

Research Fund Open Technique 52

The AI Alignment Forum

MARCH 28, 2025

And a technical note: it needs to be in some first-order system or alternatively, you need to measure proof checking time as opposed to proof length. Daniel Filan (00:28:50): If people remember my singular learning theory episodes , theyll get mad at you for saying that quadratics are all there is, but its a decent approximation. (00:28:56):

Model 52

Model Network Training Train 52