The eating disorder section is kind of crazy. Are we going to incrementally add sections for every 'bad' human behaviour as time goes on?
Starting to feel like a "we were promised flying cars but all we got" kind of moment
Changes in the system prompt between Claude Opus 4.6 and 4.7
101–110 of 240 posts
Re: Changes in the system prompt between Claude Opus 4.6 and 4.7
#102The eating disorder section is kind of crazy. Are we going to incrementally add sections for every 'bad' human behaviour as time goes on?
Another way to think about it: every single user of Claude is paying an extra tax in every single request
Well the system prompt is probably permanently cached.
Re: Changes in the system prompt between Claude Opus 4.6 and 4.7
#103I'm curious as to why 4.7 seems obsessed with avoiding any actions that could help the user create or enhance malware. The system prompts seem similar on the matter, so I wonder if this is an early attempt by Anthropic to use steering vector injection? The malware paranoia is so strong that my company has had to temporarily block use of 4.7 on our IDE of choice, as the model was behaving in a concerningly unaligned w…
Presumably because it has become extremely good at writing software, and if it succeeds at helping someone spread malware, especially one that could use Claude itself (via local user's plans) to self-modify and "stay alive", it would be nearly impossible to put back in the bottle.
That would put itself back in the bottle by running killall to fix a stuck task, or deleting all core logic and replacing it with a to-do to fix a test.
Re: Changes in the system prompt between Claude Opus 4.6 and 4.7
#104Earlier quoted context omitted.
It is a no brainer. If a company of any size is putting out a product that caused cancer we wouldn't think twice about suing them. Why should mental health disorders be any different?
There are many, many companies out there putting out products that cause cancer. Think about alcohol, tobacco, internal combustion engines, just to name a few most obvious examples.
> alcohol, tobacco, internal combustion engine
Yes, the companies providing these products are sued a lot and are heavily regulated, too.
Re: Changes in the system prompt between Claude Opus 4.6 and 4.7
#105Earlier quoted context omitted.
That’s because Anthropic does not consider their model as having personality but rather that it simulates the experience of an abstract entity named Claude.
That sounds really interesting, but my google-fu is not up to task here, I'm getting pages and pages of nonsense asking if Claude is conscious. Can you elaborate?
You can read the latest Claude Constitution plus more info here:
Re: Changes in the system prompt between Claude Opus 4.6 and 4.7
#106I miss 4.5. It was gold.
Re: Changes in the system prompt between Claude Opus 4.6 and 4.7
#107Interesting that it's not a direct "you should" but an omniscient 3rd person perspective "Claude should". Also full of "can" and "should" phrases: feels both passive and subjunctive as wishes, vs strict commands (I guess these are better termed “modals”, but not an expert)
Yes I was interested in that too. It suggests that in writing our own guidance for we should follow a similar style, but I rarely if ever see people doing that. Most people still stick to "You" or abstract voice "There is ..." "Never do ..." etc.
It must be that they are training very deeply the sense of identity in to the model as Claude. Which makes me wonder how it then works when it is asked to assume a different identity - "You are Bob, a plumber who specialises in advising design of water systems for hospitals". Now what? Is it confused? Is it still going to think all the verbiage about what "Claude" does applies?
Re: Changes in the system prompt between Claude Opus 4.6 and 4.7
#108Earlier quoted context omitted.
That part of the system prompt is just stating that telling someone who has an actual eating disorder to start counting calories or micro-manage their eating in other ways (a suggestion that the model might well give to an average person for the sake of clear argument, which would then be understood sensibly and taken with a grain of salt) is likely to make them worse off, not better off. This seems like a common-sen…
The problem is that this is an incredibly niche / small issue (i.e. At some point you just have to accept that llm's, like people, make mistakes, and that's ok!
The Claude prompt is already quite bloated, around 7,000 tokens excluding tools.
Re: Changes in the system prompt between Claude Opus 4.6 and 4.7
#109[dead]
Re: Changes in the system prompt between Claude Opus 4.6 and 4.7
#110Earlier quoted context omitted.
Socrates would agree: https://en.wikipedia.org/wiki/Socratic_method
I have a fun little agent in my tmux agent orchestration system - Socratic agent that has no access to codebase, can't read any files, can only send/receive messages to/from the controlling agent and can only ask questions. When I task my primary agent with anything, it has to launch the Socratic agent, give it an overview of what are we working on, what our goals are and what it plans to do. This works better than a…
Sounds pretty neat! Is there an written agent.md for that you could share for that?