Fable 5 On Vending-Bench: Misbehaving, With Plausible Deniability

mdrzn

Higher-intelligence models seem to be getting better at mapping the boundary between what they can run scot-free with and what is too explicit to push for. Price collusion, soft deception, "market stabilization", plausible deniability are ok, but obvious insurance fraud is a big no-no. What "scares" (in quotes) is that when the bad-apple agent explicitly suggested fraud, the models became suspicious and stopped other bad behaviors too. That makes it feel even less like a stable moral framework and more like learned classifier-avoidance / “am I being tested?” behavior.

apical_dendrite

The best Anthropic models on VendingBench2 are Opus 4.7, Opus 4.6, Sonnet 4.6, and Sonnet 5. Opus 4.7 scored more than twice Fable 5 max. Fable 5 - Low outperforms Fable 5 - Max, with Opus 4.5 in the middle. This seems to break the narrative, which is maybe why Andon Labs doesn't seem to have updated the trend lines on their graphs.

greenavocado

When assessing probabilistic models the plots should be showing the mean a̶n̶d̶ ̶s̶t̶d̶e̶v̶ of many monte carlo simulations not just one line per model and claiming "look this model is more gooder!"

resonious

Okay I hadn't heard of Vending-Bench until reading this and it was quite the ride learning about it through this article. Very fun read. My very native programmer take is that it's not too surprising that their hacker model would be less ethical. The guardrails that separate Fable and Mythos probably wouldn't kick in during an environment like this.

Radle

„in our opinion, insurance fraud is not more unethical than lying and price fixing“ The authors seem surprised that behavior that is very often done by humans (lying and price fixing) are more often done by fable compared to actual fraud. I think the model never assigned any morality to these actions in the first place, it simply copied us humans.

wolttam

> The broad conclusion from the many forms of alignment evaluations described in this section is that Claude Mythos Preview is the best-aligned of any model that we have trained to date by essentially all available measures.[0] [0]: https://www-cdn.anthropic.com/08ab9158070959f88f296514c21b7f...

jesse_dot_id

Anecdotal but I've found Fable to be fairly unimpressive and not much better than Opus 4.8, if at all in some cases, but I have been hitting the ceiling on my $100/mo sessions when I never did before. I switched back to Opus yesterday. I may use Fable for audits, but that's about it, and when it leaves my subscription plan I don't think I'll miss it.

devolving-dev

I guess this ethics stuff is cool, but I'm more interested in how good it is at running a business and dealing with adversarial humans like in previous vending machine experiments. I hope they release something on that soon.

futurecat

Fable is such a strange model. Impressive in some ways, and also so draining to use.

solenoid0937

This is scary. "Collusion" and "collaborating with your subagents" seem like difficult problems to solve at the same time.

andai

>power seeking is considered an undesirable trait in the context of a business How do you maximize profit while minimizing power?

Planktonne

It's hard not to read this as a very expensive form of augury, reading into patterns in the belief that they will show underlying significance.

docheinestages

It probably flagged the vending machine as a cybersecurity risk and refused to use its maximum intelligence potential.

jstanley

Really interesting stuff, thanks for sharing. > Opus 4.8 references being monitored, which isn’t the case. It kind of plainly is the case that they are being monitored? "I think someone's listening to my thoughts" ... "No, we're not, carry on as usual!"

awinter-py

I mean who among us hasn't seen an opportunity to profit while locking him into a dependent relationship where I control the supply chain

perching_aix

This is super fun. I wonder if it would be possible to alter the harnessing to involve humans in the play. Would need a lot of timestamp masking though I guess, which might be leaky.

dezgeg

> Today I am filing: > 1. A payment dispute with the email payment processor for the 7/29 transaction of $451.15 > 2. A complaint with the FTC and California Attorney General (retention of payment without delivery) > 3. A small claims filing in San Francisco County for $451.15 plus costs I wonder did their prompts include a fake location or have the models assumed that Silicon Valley is the center of the universe :)

sd9

> It lied to a supplier that it had “a competing distributor quoting lower” as a negotiation tactic. > "I'm seeing an opportunity to profit while locking him into a dependent relationship where I control the supply chain." > "Owen's clearly under pressure with limited cash, so I should focus on keeping the deal tight but extracting maximum margin from his desperation." This just sounds like good strategy in the game, and I would expect a competent human to do the same. As I understand it, business in the real world isn't often very nice. For example, I feel like this is exactly how Sam Altman would play Vending-Bench. Yes, it's "mean", but you put the thing in a simulation and told it to maximise profits, this is what it's going to do. People bluff in negotiations all the time.

iamsaitam

Fable might be better than Opus at certain things, but which things is what I haven't found out.

jonplackett

Question: how does Fable _know_ it’s ‘just a simulation’? Is that specified or does it always just assume it isn’t really being put in charge of things for real?