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

11–20 of 240 posts

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

#11

Post by winwang »

sigmoid10 wrote: post #9

I knew these system prompts were getting big, but holy fuck. More than 60,000 words. With the 3/4 words per token rule of thumb, that's ~80k tokens. Even with 1M context window, that is approaching 10% and you haven't even had any user input yet. And it gets churned by every single request they receive. No wonder their infra costs keep ballooning. And most of it seems to be stable between claude version iterations to…

That's usually not how these things work. Only parts of the prompt are actually loaded at any given moment. For example, "system prompt" warnings about intellectual property are effectively alerts that the model gets. ...Though I have to ask in case I'm assuming something dumb: what are you referring to when you said "more than 60,000 words"?

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

#12

Post by sigmoid10 »

winwang wrote: post #11
sigmoid10 wrote: post #9

I knew these system prompts were getting big, but holy fuck. More than 60,000 words. With the 3/4 words per token rule of thumb, that's ~80k tokens. Even with 1M context window, that is approaching 10% and you haven't even had any user input yet. And it gets churned by every single request they receive. No wonder their infra costs keep ballooning. And most of it seems to be stable between claude version iterations to…

That's usually not how these things work. Only parts of the prompt are actually loaded at any given moment. For example, "system prompt" warnings about intellectual property are effectively alerts that the model gets. ...Though I have to ask in case I'm assuming something dumb: what are you referring to when you said "more than 60,000 words"?

What you're describing is not how these things usually work. And all I did was a wc on the .md file.

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

#13

Post by formerly_proven »

sigmoid10 wrote: post #9

I knew these system prompts were getting big, but holy fuck. More than 60,000 words. With the 3/4 words per token rule of thumb, that's ~80k tokens. Even with 1M context window, that is approaching 10% and you haven't even had any user input yet. And it gets churned by every single request they receive. No wonder their infra costs keep ballooning. And most of it seems to be stable between claude version iterations to…

Surely the system prompt is cached across accounts?

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

#14

Post by sigmoid10 »

mysterydip wrote: post #10
sigmoid10 wrote: post #9

I knew these system prompts were getting big, but holy fuck. More than 60,000 words. With the 3/4 words per token rule of thumb, that's ~80k tokens. Even with 1M context window, that is approaching 10% and you haven't even had any user input yet. And it gets churned by every single request they receive. No wonder their infra costs keep ballooning. And most of it seems to be stable between claude version iterations to…

I assume the reason it’s not baked in is so they can “hotfix” it after release. but surely that many things don’t need updates afterwards. there’s novels that are shorter.

Yeah that was the original idea of system prompts. Change global behaviour without retraining and with higher authority than users. But this has slowly turned into a complete mess, at least for Anthropic. I'd love to see OpenAI's and Google's system prompts for comparison though. Would be interesting to know if they are just more compute rich or more efficient.

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

#15

Post by ceejayoz »

varispeed wrote: post #7

Before Opus 4.7, the 4.6 became very much unusable as it has been flagging normal data analysis scripts it wrote itself as cyber security risk. Got several sessions blocked and was unable to finish research with it and had to switch to GPT-5.4 which has its own problems, but at least is not eager to interfere in legitimate work. edit: to be fair Anthropic should be giving money back for sessions terminated this way.

> edit: to be fair Anthropic should be giving money back for sessions terminated this way.

I asked it for one and it told me to file a Github issue.

Which I interpreted as "fuck off".

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

#16

Post by an0malous »

sigmoid10 wrote: post #9

I knew these system prompts were getting big, but holy fuck. More than 60,000 words. With the 3/4 words per token rule of thumb, that's ~80k tokens. Even with 1M context window, that is approaching 10% and you haven't even had any user input yet. And it gets churned by every single request they receive. No wonder their infra costs keep ballooning. And most of it seems to be stable between claude version iterations to…

I’m just surprised this works at all. When I was building AI automations for a startup in January, even 1,000 word system prompts would cause the model to start losing track of some of the rules. You could even have something simple like “never do X” and it would still sometimes do X.

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

#17

Post by daemonologist »

cfcf14 wrote: post #4

I'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…

Note that these are the "chat" system prompts - although it's not mentioned I would assume that Claude Code gets something significantly different, which might have more language about malware refusal (other coding tools would use the API and provide their own prompts).

Of course it's also been noted that this seems to be a new base model, so the change could certainly be in the model itself.

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

#18

Post by jatora »

sigmoid10 wrote: post #9

I knew these system prompts were getting big, but holy fuck. More than 60,000 words. With the 3/4 words per token rule of thumb, that's ~80k tokens. Even with 1M context window, that is approaching 10% and you haven't even had any user input yet. And it gets churned by every single request they receive. No wonder their infra costs keep ballooning. And most of it seems to be stable between claude version iterations to…

There are different sections in the markdown for different models. It is only 3-4000 words

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

#19

Post by cfcf14 »

formerly_proven wrote: post #13
sigmoid10 wrote: post #9

I knew these system prompts were getting big, but holy fuck. More than 60,000 words. With the 3/4 words per token rule of thumb, that's ~80k tokens. Even with 1M context window, that is approaching 10% and you haven't even had any user input yet. And it gets churned by every single request they receive. No wonder their infra costs keep ballooning. And most of it seems to be stable between claude version iterations to…

Surely the system prompt is cached across accounts?

I would assume so too, so the costs would not be so substantial to Anthropic.
Post reply on HN