Phemist
As discussed here:
https://cyberplace.social/@GossiTheDog/117528831681803563
and as can be seen as there is no version 2.1.313 here: https://open-vsx.org/extension/Anthropic/claude-code/2.1.313
but there is https://open-vsx.org/extension/Anthropic/claude-code/2.1.314 https://open-vsx.org/extension/Anthropic/claude-code/2.1.312
Reading further:
It seems that this is part of a european "habitats directive" for managing biodiversity within Europe. This directive (according to the above paper) determined there need to be around 500 wolf packs across Europe to keep wolves at a stable level without too much inbreeding. The Netherlands was found to be able to "contribute" 23 to 56 wolf packs in this sense.
So I agree they are liable because they chose to build the AI, but they also literally told the AI to hack.
My idea would be that the ngram size over which the watermarking works is necessarily limited in order to resist edits better. It might be possible to lead the model to trigger the refusal in the form of these specific ngrams, the completion of which is then more likely flipped to compliance (due to the logit bias introduced by the watermarking), making hazardous requests systematically more likely to be accepted?
Also interested in how this watermarking push makes sense when considering RSI.
Detection of watermarking requires access to the watermarking key, a secret in the current suggested scheme (leaking it would amount to being able to strip the watermark).
So, there will need to be a watermark checking service. The checking service will of course be rate-limited for common folk (and model distillers). OpenAI/Anthropic/Google/other privileged model builders need to filter out AI slop at scale, so need access to others' service without rate-limits (or the watermarking keys need to be shared).
This creates an in-group with pristine datasets, and an outgroup whose models will collapse on the slop outputs with no good ability to filter.
In your analogy: What if seed 42 specifically causes poor quality behaviour (in some contexts specifically). Normally, these quality differences will be washed out because the seed is random, now it is no longer random, so shouldnt we check into specific behaviour under this specific seed?
My comment and the other replies show you how to use git to check and clean the files of the much maligned horked build script. These will work regardless of the gitignore contents.
But then again, pretty sure you are just having a laugh at our expense by taking this ridiculous position.
https://github.com/incoai/splash/issues/38
Looks like an issue exists to convert model weights for ornith1.5 as this is a magical process atm.
Also you can do `git status --ignored` and it will list all files changed, even if ignored. If that is really your main issue.
Basically is a prompt-your-own truman show. Prompting is relatively slow and crashy, so it is hard to build continuity.
Truman is basically dragged back-and-forth between 3 or 4 separate stories at the same time. One person was essentially trying to get truman to break its own simulation by asking what it would prompt after opening the trumanworld.live website on his phone. Interspersed with this, truman kept throwing fruit on the ground and yelling I CHOOSE YOU BULBASAUR/SQUIRTLE/PIKACHU. At one point truman looked at the camera and said "STOP WITH THE POKEMON ALREADY, DIGIMON ARE THE CHAMPION". Another thread was truman constantly breaking out into a musical song. A song about bananas got mixed with the simulation breaking attempts and truman ended up singing something like "This is how I feel. Like the skin of banana, away the reality I peel (and then proceeded to pick up his phone and open the trumanworld.live site again, attempting to self-prompt).
It's chaotic and pretty fun!
The advertiser can buy logit "boosts" to specific tokens in a given context (the more preceding context, the cheaper). Once an activation has happened, dont do it again for the session.
The LLM will end up pushing a specific product contextual to the conversation. It just needs this slight nudge at the logit level to start talking about it and will fill in the rest.
> not wanting to give the user the feeling they are doing something definitive
In their refusal, while (accidental) acceptance is always definitive...
EDIT: In another thread this is called the ratchet of consent. Apt.
I feel this pattern is really abusive. Like I am offering to slap you in the face, giving you two answer options: Yes and "Maybe later/no, thank you". As though you have any obligation to be forced to answer this question again at some late time, or to be very polite while you refuse to be slapped in the face. The correct answer is obviously "No, fuck off".