Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Changes in the system prompt between Claude Opus 4.6 and 4.7

simonwillison.net

Post reply on HN
Print view View original

121–130 of 240 posts

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#121

Post by wongarsu »

dhedlund wrote: post #50
chatmasta wrote: post #47

Earlier quoted context omitted.

Claude Code system prompt diffs are available here: https://cchistory.mariozechner.at/?from=2.1.98&to=2.1.112 (URL is to diff since 2.1.98 which seems to be the version that preceded the first reference to Opus 4.7)

The "Picking delaySeconds" section is quite enlightening. I feel like this explains about a quarter to half of my token burn. It was never really clear to me whether tool calls in an agent session would keep the context hot or whether I would have to pay the entire context loading penalty after each call; from my perspective it's one request. I have Claude routinely do large numbers of sequential tool calls, or have…

They really should have just set the cache window to 5:30 or some other slightly odd number instead of using all those tokens to tell claude not to pick one of the most common timeout values

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#122

Post by wongarsu »

jug wrote: post #112
embedding-shape wrote: post #28

Earlier quoted context omitted.

Two things; the model and runtime matters a lot, smaller/quantized models are basically useless at strict instruction following, compared to SOTA models. The second thing is that "never do X" doesn't work that well, if you want it to "never do X" you need to adjust the harness and/or steer it with "positive prompting" instead. Don't do "Never use uppercase" but instead do "Always use lowercase only", as a silly examp…

It's interesting to note here that Anthropic indeed don't use "do not X" in the Opus system prompts. However, "Claude does not X" is very common.

I suspect that lets the model "roleplay" as Claude, promoting reasoning like "would Claude do X?" or "what would Claude do in this situation?"

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#123

Post by wongarsu »

clickety_clack wrote: post #80
lkbm wrote: post #35

Earlier quoted context omitted.

Yes, but doesn't the token change mean that?

You can train a tokenizer on old data just like you can train a model on old data.

But you can't use an old model with a new tokenizer. Changing the tokenizer implies you trained the model from scratch

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#124

Post by niobe »

embedding-shape wrote: post #6

> The new section includes: When a request leaves minor details unspecified, the person typically wants Claude to make a reasonable attempt now, not to be interviewed first. Uff, I've tried stuff like these in my prompts, and the results are never good, I much prefer the agent to prompt me upfront to resolve that before it "attempts" whatever it wants, kind of surprised to see that they added that

Having to "unprompt" behaviour I want that Anthropic thinks I don't want is getting out of hand. My system prompts always try to get Claude to clarify _more_.

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#125

Post by bartread »

embedding-shape wrote: post #6

> The new section includes: When a request leaves minor details unspecified, the person typically wants Claude to make a reasonable attempt now, not to be interviewed first. Uff, I've tried stuff like these in my prompts, and the results are never good, I much prefer the agent to prompt me upfront to resolve that before it "attempts" whatever it wants, kind of surprised to see that they added that

[dead]

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#126

Post by whateveracct »

dymk wrote: post #116
teaearlgraycold wrote: post #102

Earlier quoted context omitted.

Well the system prompt is probably permanently cached.

Takes up a portion of the context window, though

And the beginning of the context window gets more attention, right?

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#127

Post by Havoc »

>“If a user indicates they are ready to end the conversation, Claude does not request that the user stay in the interaction or try to elicit another turn and instead respects the user’s request to stop.”

Seems like a good idea. Don't think I've ever had any of those follow up suggestions from a chatbot be actually useful to me

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#128

Post by chermi »

gck1 wrote: post #56
embedding-shape wrote: post #6

> The new section includes: When a request leaves minor details unspecified, the person typically wants Claude to make a reasonable attempt now, not to be interviewed first. Uff, I've tried stuff like these in my prompts, and the results are never good, I much prefer the agent to prompt me upfront to resolve that before it "attempts" whatever it wants, kind of surprised to see that they added that

I even have a specific, non-negotiable phase in the process where model MUST interview me, and create an interview file with everything captured. Plan file it produces must always include this file as an artifact and interview takes the highest precedence. Otherwise, the intent gets lost somewhere in the chat transcript.

The raw Q&A is essential. I think Q & Q works so we'll because it reveals how the model is "thinking" about what you're working on, which allows for correction and guidance upfront.

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#129

Post by zythyx »

jeffrwells wrote: post #66
walthamstow wrote: post #24

The 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

Isn't it basically the same as paying dust to crypto exchanges when making a transaction - it's so miniscule that it's not worth caring about?

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#130

Post by WarmWash »

goosejuice wrote: post #69
WarmWash wrote: post #41

Earlier quoted context omitted.

When you are worth hundreds of billions, people start falling over themselves running to file lawsuits against you. We're already seeing this happen. So spending $50M to fund a team to weed out "food for crazies" becomes a no-brainer.

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?

I think a more apt analogy would be suing a vaccine manufacturer after it gave you adverse effects, when you also knew you were high risk before that.
Post reply on HN