Top postsTop post
Epistemic status: Draft-Quality. Partially motivated reasoning. After my “Not Pinning Your OpenRouter Provider Might Invalidate Your Research” post, a representative of an AI marketplace reached out to me about providers and reproducibility. I unofficially chatted with a representative there[1] about this essay, but they do not endorse this document.[2] This...
Please share this with anyone doing AI research with 3rd party providers so that they can ensure their research won’t be corrupted. * When you ask OpenRouter[1] to give you tokens from a given model, OpenRouter sends your request to a random available provider. * OpenRouter providers have variable quality....
If you told an AI Alignment researcher in 2018 about an alignment plan that involved collecting trajectory information of moral experts at scale and training an AI to copy it, they would point out that this would not scale to superintelligence. This is essentially what major AI Labs and most...
Epistemic Status: I wrote this for an application then realized it might be of interest to others or spark a conversation. Yoshua Bengio and LawZero are important players in AI Safety, so I think we should have a conversation about their ideas. I have two substantial concerns with Yoshua Bengio’s...
Status: Very early days of the research. No major proof of concept yet. The aim of this research update is to solicit feedback and encourage others to experiment with my code. GitHub repository Main Idea: Researchers are using SAE latents to steer model behaviors, yet human-designed selection algorithms are unlikely...
Gulsimo Osimi, Matthew Khoriaty Executive Summary This research investigates the potential of collaborative AI systems to solve complex tasks through the orchestration of multiple specialized models. By leveraging Microsoft's Autogen framework, we coordinate DeepSeek and GPT-4o Mini to tackle complex challenges. Beyond performance enhancement, our work makes a novel contribution...