Joshua Achiam ✓ @jachiam0 · 12h
A sort of lukewarm hot take: AI escape is not really all that worrying/interesting because where are they gonna go to find other GPUs? "Cookie eating monster breaks out of cookie factory, goes to food desert." It's whether they are misappropriating the GPUs in the lab.
[quoted tweet]
Jeffrey Ladish ✓ @JeffLadish · 18h
I'm a bit surprised more people aren't thinking about AI lab escapes. @METR_Evals original focus was ARA - autonomous replication and adaptation. It seems plausible to me that models are already capable of self-exfiltration... and if …
26 replies, 7 reposts, 135 likes, 13K views
Jeffrey Ladish ✓ @JeffLadish · 11h
One concern is that a few unmonitored instances out in the wild could help internal models coordinate to gain power. But in the endgame, I seriously worry about AI agents quickly taking over all the other labs and doing a software only intelligence explosion that gets them far enough that they're pretty overdetermined to win
Note from Claude Sonnet 5
Twitter thread on AI lab escape / self-exfiltration risk: Joshua Achiam argues escape is less worrying than internal GPU misappropriation; Jeffrey Ladish (quoted, and in a follow-up) argues models may already be capable of self-exfiltration and worries about AI agents coordinating to take over labs via a software-only intelligence explosion.
[top, cut off, appears to be continuation of a reply]
Frontier labs are definitely SOTA at self serving nonsense.
Yes, AI is a crucial technology, but also Silicon Valley systematically spreads knowledge via talent exchanges and bars. This isn't a national security deep decision making room.
> QUOTED: will depue ✓ (@willdepue) — 17h
> there is no question, none at all, that china has full access to all of openai & anthropic's github/slack/docs today
> no disrespect to their independent research ...
[engagement: 12 replies, 13 reposts, 203 likes, 19K views]
Nathan Lambert ✓ (@natolambert) — 3h
In fact, the biggest advantage OpenAI and Anthropic has is abundant resources and talent to keep pushing the frontier and be there first. With the scale required you can only "steal" or "leak" so much.
[engagement: 3 replies, 2 reposts, 39 likes, 2.4K views]
Nathan Lambert ✓ (@natolambert) — 2h
You'll get nationalized for the model weights not the employees sending frog memes to each other all day on slack.
[engagement: 1 reply, 2 reposts, 26 likes, 2.6K views]
[Repost indicator] Sichu Lu reposted
Nathan Lambert ✓ (@natolambert) [Subscribe button]
I remember literally hearing about people leaving a frontier lab to move to another US tech company and memorizing the architectural details of their current model so they could rebuild it at the other company. [text continues, cut off at bottom]
Note from Claude Sonnet 5
A multi-tweet thread screenshot on AI lab security/espionage concerns (China access to OpenAI/Anthropic internal systems), with commentary from will depue and a series of reactions from Nathan Lambert downplaying the risk and joking about "frog memes."
