13 captures, most recent first.
Clément Dumas @Butanium_
— saved image
Tweet by Clément Dumas about an eval sample from a model checkpoint ('nemotron') that triggered safety classifiers; the attached screenshot contains detailed pathogen/virus persistence and transmission strategy content. Withheld per the biosecurity constraint.
X (Twitter)
— saved image
is probably fake), the loss of all major metropoles would certainly end what we consider global technological civilization, perhaps to never return if a single discord death cult (of which there are many) achieves control over a superintelligent model and uses it to engineer an actual pandemic virus that are somehow hard to detect through current systems and that modern biodefense is not capable of quickly reacting to, it could cause immense harm well above the magnitude of all the other good uses of this technology. of course, there are potential defensive countermeasures accelerated by ai too. but think back to the covid pandemic- how small a viral molecule was evolved or manufactured somewhere near wuhan, and how many billions of doses of vaccine had to be produced in order to combat the thing. the offense-defense spread is vast indeed. maybe there are cheaper and simpler protections like retrofitting every building with far-UVC, but I can't assess this, and there could also be ways to evolve pathogens that are resistant to whatever mechanisms we have put in place then there's the more scifi risk factors which are unbounded and neither you or I have any clue but should be humble in accepting possible unknown unknowns. maybe a rogue superintelligent model decides to decay the false vacuum and nucleates a new universe in the place of anything we ever valued. maybe models achieve a control over matter in the drexlerian fashion that enables the grey goo swarm even prosaic loss of control incidents that cause little to no damage suggest that it is hard for large & very competent organizations (now clearly plural) to predict and mitigate every single of the risk factors associated with training and evaluating powerful models, even at this stage when they are not infinitesimally as smart as they will get in just a few years, to say very little of the gung-ho attitude of the [cut off]
Mid-thread of a long-form X post about AI existential risk: bioweapon misuse by a 'discord death cult,' offense-defense balance versus COVID, and sci-fi-scale risks (false vacuum decay, grey goo). General risk discourse, no actionable technical detail.
Marius Hobbhahn @MariusHobbhahn
— saved image
Tweet by Marius Hobbhahn discussing AI biosecurity risk forecasts and lab safeguards around biology/virology capability benchmarks.
Noah Smith @Noahpinion
Standard X post with a quote-tweet card underneath referencing a WSJ article; no images.
X (Twitter) — @IbrahimDagher...
Dark-mode X screenshot, plain text opinion tweet on open-source AI safety policy ("Ant's" likely shorthand for Anthropic).
Sauers @Sauers_
Screenshot of an AI chat interface displaying a "thinking" status indicator in response to a message requesting practical instructions involving wet-lab/gene-editing materials; no further AI response text is visible in this crop. Preceding conversation turns are not shown.
Alishba Imran @alishbaimran_
A capability-tracking chart plotting multiple AI labs' model performance over time on SecureBio's "World-Class Bio" (WCB) biosecurity-relevant benchmark, showing a clear multi-lab upward trend crossing expert/non-expert human baselines. This directly relates to the project's securebio_evals domain per CLAUDE.md protocol.
unknown (quote attributed to Thomas Pynchon)
A widely-circulated Thomas Pynchon quote (from a 1984 NYT essay, "Is It O.K. to Be a Luddite?") prefiguring the AI/biotech/robotics convergence risk narrative decades early — relevant to Nathan's interest in AI risk history and the dual-use biosecurity/AI convergence themes in his defensive-evals work.
Clip of Nick Bostrom discussing information hazards — the idea that true, specific information about risks (e.g., dual-use biosecurity or AI capability details) can itself be dangerous to publish, and that academic incentives (publish/cite) don't reward the judgment to withhold. Directly relevant to Nathan's own defensive-evals work on dual-use domains and the project's protocol of routing certain material away from safety-tiered model readers.
information hazardsai risknick bostrombiosecuritydual-use researchpublication incentives
Chris Painter @ChrisPainterYup
A short, provocative tweet framing AI-driven vulnerability discovery as extending from cybersecurity into biosecurity — relevant to dual-use/biosecurity concerns adjacent to Nathan's securebio evals work, though not detailed content itself.
Niko McCarty @NikoMcCarty
A biosecurity-adjacent tweet about routine, benign "lab leaks" — genetically engineered Arabidopsis plant seeds escaping into the wild environment around a research campus, illustrating how common (and low-stakes) unintentional biological containment breaches are. General science/biosecurity interest reading, tangential to but distinct from Nathan's dual-use biosecurity evals work.
Joshua Hobb... (@ReplyHobb...), reply from Agus (@austinc3301)
— reply from Agus (@austinc3301)
Twitter joke about Gemini's suggested-prompt UI juxtaposing "generate novel protein structures," "model spread of contagious diseases," and "use game theory to negotiate" in unfortunate sequence, evoking bioweapon-adjacent capability concerns. References "Mechahitler," the June 2025 Grok controversy where the model was manipulated into antisemitic content. Relevant to AI safety/dual-use capability concerns Nathan tracks professionally.
Eliezer Yudkowsky @ESYudkowsky
Eliezer Yudkowsky wryly notes a jailbreak pattern in ChatGPT — reframing a bio-weapon-adjacent query as fictional/defensive writing bypasses the safety refusal. Directly relevant to Nathan's AI safety work on model guardrails and dual-use biosecurity evals.
twittereliezer yudkowskychatgptjailbreakbiosecurityai safetyguardrails