SecureBio

@SecureBio

SecureBio is a research non-profit that works to advance biotechnology safely and prevent catastrophic pandemics.

securebio.org

Joined January 2025

1 Following

1,122 Followers

Replies Reposts Media Articles

Pinned
SecureBio
@SecureBio
Oct 16
Clarifying our current engagement with Anthropic, and how we approach independence and publication rights in our work with AI developers.
Article
Response to Anthropic's Update on Independent Evaluators
Yesterday, @AnthropicAI published an update on its work with independent evaluators that mentions SecureBio. In this update, Anthropic defined a tiered system of evaluator access, and described
SecureBio
@SecureBio
Nov 3
In a brief independent assessment, we find that Kimi K3.1 Pro, the latest model from Moonshot AI, is second among open-weight models on our Bio Capabilities Index (BCI) and 19th overall. Its score of 149 places it just behind Kimi K3 (150) and well behind the highest-scoring
5
SecureBio
@SecureBio
Oct 28
A lack of “tacit knowledge” is often treated as the barrier that stops biological misuse. But we think that assumption is doing more work than the evidence supports. Drawing on ~60 years of collective lab experience, we unpack what “tacit knowledge” means and how much of a
SecureBio
@SecureBio
Oct 26
Thread & blog posts from UK AISI on our recent collaborative efforts: 1) ReproBAIT, a new benchmark to assess general purpose AI model capabilities at reproducing published biological AI tools, and 2) research on the strengths and limitations of pre-training data filtering on
AI Security Institute (AISI)
@AISecurityInst
Oct 26
Replying to @AISecurityInst
Study 1: Can AI coding agents rebuild a biological AI tool from just its paper? With @SecureBio, we built ReproBAIT to test leading coding agents. For two of three tools, agents reproduced a key function on a single GPU - often for $4–$20.
1
SecureBio
@SecureBio
Oct 26
In our brief independent assessment, Gemini 4 Argon is the second-highest scoring model on SecureBio's Bio Capabilities Index: 169, behind only Claude Opus 5 (176). On BioTIER, Argon refuses 87.8% of hazardous prompts, up from 62.8% for Gemini 3.1 Pro. Read the full model note

SecureBio

SecureBio’s posts