The article explores three approaches to agent corrigibility: shards, simulators, and singular learning. The author discusses the possibility of implementing a corrigible agent considering recent theories about large language model learning.
The chart will appear after repeat observations. The current metric comes from the source.
8 source pointsReal observations only. History before source connection is not reconstructed.
Understanding different approaches to corrigibility can aid in developing safer and more controllable AI systems.
Anthropic released documents related to a copyright litigation case. The documents outline the company's research plans from 2021, including the development of a safe general AI assistant capable of programming tasks. The documents do not represent the company's official stance.
yesterdayLessWrongThe article discusses challenges in ensuring the individual rationality of safe Pareto improvements (SPIs) in agent interactions. It explores mechanisms that might lead agents to prefer opting out of SPIs, including effects on other participants' strategies and potential consequences of not participating in SPIs.
2 days agoLessWrongAs part of the MATS 9.1 extension program, mentored by Richard Ngo, this work explores applying the concept of cross-temporal incoherence to multistage games with observable actions. New equilibria defined through variants of the One Shot Deviation Principle (OSDP) are proposed, allowing analysis of situations where players reach inadequate equilibria with their future or counterfactual selves despite time-consistent discounting. The potential contributions of these variants to a theory of credible threats are also discussed.
2 hours agoHacker NewsA tool is presented that allows AI agents to paint large arrows, boxes, and text on the screen.
6 days agoLobstersThe article discusses the limitations and shortcomings of coding agents, highlighting why they often fail to perform effectively in real-world programming tasks.
6 days agoHugging Face BlogFast private agents operating on-device using the LFM2.5-24B-A2B model are presented.
2 days ago