Max Bodach

What biases do AIs have? It turns out, AIs show strong favoritism toward specific people, countries, and companies. Our interactive AI Values Dashboard tracks who Claude Fable and other AIs favor most. Keep scrolling to learn who is Fable’s favorite politician 🧵

I’ve had a number of conversations with folks inside and outside government about the current situation with Anthropic, and here is what I believe to be true: — As we know, Anthropic publicly released its Mythos class models earlier this week under the commercial name Fable. — Fable is Mythos with guardrails. But if those guardrails fail, then you’ve exposed Mythos and its advanced cyber capabilities to people who shouldn’t have them. (Keep in mind that Anthropic itself widely promoted the idea that Mythos was a cyberweapon and needed to be regulated as such. They asked for government regulation of Mythos and championed the guardrails on Fable. If there is a vulnerability — big or small — it is Anthropic’s responsibility to patch.) — A highly credible trusted partner of both Anthropic and the USG who was testing Fable came forward with a jailbreak of those guardrails. The Admin asked Dario to fix the jailbreak or de-deploy the model. Dario refused. — In their blog post, Anthropic defended its decision by saying the jailbreak isn’t serious. That is not what the trusted partner and the USG believe; nor is that kind of minimizing language consistent with Anthropic’s brand as the AI safety company. It’s difficult to fathom how they could claim a jailbreak allowing operability of a cyber weapon could be defined as not “serious.” — In the past, Anthropic has always said that safety must be top priority and taken super seriously. In this case, Anthropic prioritized the continued offering of the consumer model over safety. — In reaction, the Admin issued the export control. The Admin did this reluctantly. It’s been very surprised that Anthropic hasn’t wanted to cooperate with a reasonable safety request (ie fixing the jailbreak issue). Anthropic’s reaction is very much at odds with their branding and ethos as a safe AI research community. — The Admin’s hope now is that Anthropic remediates the safety issue, the export control is lifted, and Fable goes back into general release. The Admin wants all of this to happen as soon as possible. It is frankly bewildered that Anthropic hasn’t wanted to comply with safety requests that it previously said were its highest priority. — Those trying to misdirect and tie this action to the prior DoW/Anthropic issues are wrong. The Admin values Anthropic’s technical capabilities and feels that this issue, while serious, should be easily resolved. The ball is in Anthropic’s court.

The sheer scale of a trillion dollars can be hard to comprehend. Let me put it in perspective. You would have to earn a dollar a year for a trillion years straight to have that much money.

welcome to ai policy without training wheels

1/5: AI safety advocates worry about AI being too anthropomorphic, or about AI having a personality at all. But what if AI having a robust personality is the solution? Post-training requires persona selection, and personality design could be the way safety guidelines actually stick, the way discretion gets operationalized across every conversation. In my latest, I argue that child safety debates should focus on engineering better AI personalities rather than trying to ban them: 🧵

Re the Fable ML sandbagging, the model's AI research capabilities were probably at least partly trained on Anthropic employees diffing atop proprietary algos and infra. So the IP leak is somewhat like a researcher who knows Anthropic's stack getting poached to another lab. Anthropic's recent "When AI builds itself" post talks about a next-step eval. Where they snapshot a research session at the moment a human researcher made a suboptimal next-step choice, show a model only the transcript up to that point and ask what it would do next, then have a hindsight-equipped LLM judge decide whether the model's suggestion or the human's actual choice was better. This eval seems like a very good RL target for AI R&D - one among many that could be used to have AIs emulate Anthropic researchers and their research products. I'm just speculating. But if this was a motivation, then Anthropic should have figured out a better way to protect IP than sandbagging without telling the user they're sandbagging, which is very hostile and untrustworthy behavior.