Claude Fable 5

Update in case anyone reads this comment ever again.

I have found that I trigger the guardrails any time I ask for medical Q&A as a doctor, be it ECGs, case reports, and so on. But if I phrase it like I'm the patient ("help me interpret this ECG my doctor gave me"), then I usually get one or two answers out before hitting the guardrails.

It seems like the direction that triggers it is anything in the direction of making a diagnosis. As an MD, the fact that the paradigm of "LLMs shouldn't diagnose" has gone this far fills me with despair. The latest generation of LLMs are in fact truly excellent at diagnosis, and I know many of my colleagues, particularly those in primary care, regularly use LLMs to brainstorm. There is nothing wrong whatsoever with LLMs making diagnosis, the only caveat is that they have to be correct. This is the terrifying reality that MDs face every day and I get that the labs are hesitant about it, but as the current literature points to LLMs in fact being mostly superior to most doctors, ablating this capability is starting to get increasingly unethical. And frankly, it is also kind of insulting, both to MDs and patients, as it echoes paternalistic attitudes about medicine the field has been working for decades to move away from. Now those misguided attitudes have somehow become institutionalized as the dominant paradigm of "alignment". The nightmare scenario is that I have to be a "trusted" user in order to use the model for medicine. This gatekeeping of medical advice is profoundly unethical with regards to everyone that does not have immediate access to an MD.

And the whole thing makes even less sense when triggering the guardrails leads to a downgrade of the response by defaulting to Opus. How exactly is giving WORSE medical advice in any way related to safety and alignment? If anyone at anthropic ever reads this, please, please just abandon the paradigm that refusing to make diagnoses is in any way equivalent to alignment, it is profoundly misguided.

진심으로 한심한 모델

내 프로젝트의 있는 취약점 찾아달라는 말만 해도 안전 코드로 4.8로 모델 강제 전환시키고, 이후로 취약점과 완전히 무관한 상식적인 대화를 해도 앞 턴에 있었던 안전 코드 때문에 진행도 안됨. 도대체 이딴 누더기 수준의 안전 장치로 뺄 거면 뭐하러 뺌? 대화 조금만 진행되도 자동으로 모델 다운 시켜서, 할 줄 아는거라곤 돈만 많이 쳐먹고 개발 수준 조금 더 나아지는거? 상식적으로 내 프로젝트에, 내 소스코드를 다 보고 있는 상태로 문제를 찾는데 이것도 하지 말라면 도대체 뭘 하라는거임? 엔트로픽 이 새끼들 하는 짓이 갈 수록 열 받네.

Ok but isn’t that true of all software development? It’s not like anybody’s done a rigorous test of writing their entire codebase in Python vs Java. It’s all vibes based there. People create post-hoc justifications for why they use certain technologies but the reality is a lot more vibes than anything else.

One does not need to be able to create it themselves to evaluate if the output is correct. Consider for example that you can easily determine if a meal tastes delicious without being an expert chef, or the fact that NP problems are very difficult to solve but make for easily verifiable solutions.

IMO we are reaching the point where AI models are simply a commodity. Opus (since ~4.6) is sufficient for everything I tried coding wise. I use it to write features (but I review and understand every line it spits out) and to review code.

For code review I also still review everything myself, but use Opus to catch stuff I missed and to judge if a PR is even ready for me to review.

After just updating Claude Code to the latest version I thought about picking Fable (the bigger model) instead of Opus.

But I have no reason to. Opus does everything I want it to do. It could do it faster - that would be an improvement. But for the normal stuff we reached the point where better models are not worth it IMO.

There still might be cases where you want to throw Fable at it.