41–50 of 264 posts
We should do better than giving the models a portion of good training data or a new mitigating system prompt.
>Claude shows a striking “spiritual bliss” attractor state in self-interactions. When conversing with other Claude instances in both open-ended and structured environments, Claude gravitated to profuse gratitude and increasingly abstract and joyous spiritual or meditative expressions.
Given the cited stats here and elsewhere as well as in everyday experience, does anyone else feel that this model isn’t significantly different, at least to justify the full version increment? The one statistic mentioned in this overview where they observed a 67% drop seems like it could easily be reduced simply by editing 3.7’s system prompt. What are folks’ theories on the version increment? Is the architecture sig…
It's a small step for model intelligence but a huge leap for model usability.
Given the cited stats here and elsewhere as well as in everyday experience, does anyone else feel that this model isn’t significantly different, at least to justify the full version increment? The one statistic mentioned in this overview where they observed a 67% drop seems like it could easily be reduced simply by editing 3.7’s system prompt. What are folks’ theories on the version increment? Is the architecture sig…
Given the cited stats here and elsewhere as well as in everyday experience, does anyone else feel that this model isn’t significantly different, at least to justify the full version increment? The one statistic mentioned in this overview where they observed a 67% drop seems like it could easily be reduced simply by editing 3.7’s system prompt. What are folks’ theories on the version increment? Is the architecture sig…
Just anecdotal experience, but this model seems more eager to write tests, create test scripts and call various tools than the previous one. Of course this results in more roundtrips and overall more tokens used and more money for the provider. I had to stop the model going crazy with unnecessary tests several times, which isn't something I had to do previously. Can be fixed with a prompt but can't help but wonder if…
When I was playing with this last night, I found that it worked better to let it write all the tests it wanted and then get it to revert the least important ones once the feature is finished. It actually seems to know pretty well which tests are worth keeping and which aren't.
(This was all claude 4 sonnet, I've barely tried opus yet)
In this case, the opening sentence "People sometimes strategically modify their behavior to please evaluators" appears to be sufficient. I searched on Google for this and every result I got was a copy of the paper. Why do Anthropic think special canary strings are required? Is the training pile not indexed well enough to locate text within it?
I know that Anthropic is one of the most serious company working on the problem of the alignment, but the current approaches seem extremely naive. We should do better than giving the models a portion of good training data or a new mitigating system prompt.
But I’m having a hard time describing and AI company “serious” when they’re shipping a product that can email real people on its own, and perform other real actions - while they are aware it’s still vulnerable to the most obvious and silly form of attack - the “pre-fill” where you just change the AI’s response and send it back in to pretend it had already agreed with your unethical or prohibited request and now to keep going.
Earlier quoted context omitted.
I'm noticing much more flattery ("Wow! That's so smart!") and I don't like it
Turns out tuning LLMs on human preferences leads to sycophantic behavior, they even wrote about it themselves, guess they wanted to push the model out too fast.
Most of us here on HN don't like this behaviour, but it's clear that the average user does. If you look at how differently people use AI that's not a surprise. There's a lot of using it as a life coach out there, or people who just want validation regardless of the scenario.
Given the cited stats here and elsewhere as well as in everyday experience, does anyone else feel that this model isn’t significantly different, at least to justify the full version increment? The one statistic mentioned in this overview where they observed a 67% drop seems like it could easily be reduced simply by editing 3.7’s system prompt. What are folks’ theories on the version increment? Is the architecture sig…
Having used claude 4 for a few hours (and claude 3.7 and gemini 2.5 pro for much more than that) I really think it's much better in ways that aren't being well captured by benchmarks. It does a much better job of debugging issues then either 3.7 or gemini and so far it doesn't seem to have the 'reward hacking' behavior of 3.7. It's a small step for model intelligence but a huge leap for model usability.
But it's different in conversational sense as well. Might be the novelty, but I really enjoy it. I have had 2 instances where it had very different take and kind of stuck with me.