Posts
Media
Videos
Starter Packs
azeem.bsky.social
@azeem.bsky.social
· Feb 28
azeem.bsky.social
@azeem.bsky.social
· Feb 27
azeem.bsky.social
@azeem.bsky.social
· Feb 26
Emergent Misalignment: Narrow finetuning can produce broadly...
We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts...
arxiv.org
azeem.bsky.social
@azeem.bsky.social
· Feb 26
azeem.bsky.social
@azeem.bsky.social
· Feb 24
azeem.bsky.social
@azeem.bsky.social
· Feb 24
azeem.bsky.social
@azeem.bsky.social
· Feb 24
azeem.bsky.social
@azeem.bsky.social
· Feb 19
Magma: A Foundation Model for Multimodal AI Agents
We present Magma, a foundation model that serves multimodal AI agentic tasks in both the digital and physical worlds. Magma is a significant extension of vision-language (VL) models in that it not...
arxiv.org