In this blog post, we analyse how the recent AI 2027 forecast by Daniel Kokotajlo, Scott Alexander, Thomas Larsen, Eli Lifland, and Romeo Dean has been discussed across Chinese language platforms. We present: 1. Our research methodology and synthesis of key findings across media artefacts 2. A proposal for how...
We study alignment audits—systematic investigations into whether an AI is pursuing hidden objectives—by training a model with a hidden misaligned objective and asking teams of blinded researchers to investigate it. This paper was a collaboration between the Anthropic Alignment Science and Interpretability teams. Abstract We study the feasibility of conducting...
We (EffiSciences) ran a hackathon at the end of the Turing Seminar in ENS Paris-Saclay and ENS Ulm, an academic course inspired by the AGISF, with 28 projects submitted by 44 participants between the 11th and 12th November. We share a selection of projects. See them all here. I think...
In this blog post, we analyse how the recent AI 2027 forecast by Daniel Kokotajlo, Scott Alexander, Thomas Larsen, Eli Lifland, and Romeo Dean has been discussed across Chinese language platforms. We present:
We conducted a comprehensive search across major Chinese-language platforms–including news outlets, video platforms, forums, microblogging sites, and personal blogs–to collect the media featured in this report. We supplemented this with... (read 3201 more words →)
We study alignment audits—systematic investigations into whether an AI is pursuing hidden objectives—by training a model with a hidden misaligned objective and asking teams of blinded researchers to investigate it.
This paper was a collaboration between the Anthropic Alignment Science and Interpretability teams.
We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objective. Our training pipeline first teaches the model about exploitable errors in RLHF reward models (RMs), then trains the model to exploit some of these errors. We verify via out-of-distribution evaluations that the model generalizes to exhibit whatever behaviors it believes RMs rate highly, including... (read 3642 more words →)
We (EffiSciences) ran a hackathon at the end of the Turing Seminar in ENS Paris-Saclay and ENS Ulm, an academic course inspired by the AGISF, with 28 projects submitted by 44 participants between the 11th and 12th November.
We share a selection of projects. See them all here.
I think some of them could even be turned into valuable blog posts, and I’ve learnt a lot by reading everything. Here are a few extracts.
David HEURTEL-DEPEIGES [link]
Basically an adaptation of the famous dictionary learning paper on vision CNN.
“When looking at 100 random features, 46 were found to be interpretable and monosemantic, [...] When doing the same experiment with 100 random neurons, 2... (read 1489 more words →)