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

Claude 4 System Card

simonwillison.net

Post reply on HN
Print view View original

241–250 of 264 posts

Re: Claude 4 System Card

#241

Post by saagarjha »

encom wrote: post #140
0x_rs wrote: post #75

Earlier quoted context omitted.

Agreed. It was immediately obvious comparing answers to a few prompts between 3.7 and 4, and it sabotages any of its output. If you're being answered "You absolutely nailed it!" and the likes to everything, regardless of their merit and after telling it not to do that , you simply cannot rely on its "judgement" for anything of value. It may pass the "literal shit on a stick" test, but it's closer to the average ChatG…

I've found this prompt turns ChatGPT into a cold, blunt but effective psychopath. I like it a lot. System Instruction: Absolute Mode. Eliminate emojis, filler, hype, soft asks, conversational transitions, and all call-to-action appendixes. Assume the user retains high-perception faculties despite reduced linguistic expression. Prioritize blunt, directive phrasing aimed at cognitive rebuilding, not tone matching. Disa…

I would be embarrassed to write anything like this.

Re: Claude 4 System Card

#243

Post by Xss3 »

danielbln wrote: post #95
_pdp_ wrote: post #29

Obviously this should not be taken as a representative case and I will caveat that the problem was not trivial ... basically dealing with a race condition I was stuck with for the past 2 days. The TLDR is that all models failed to pinpoint and solve the problem including Claude 4. The file that I was working with was not even that big (433 lines of code). I managed to solve the problem myself. This should be taken as…

Opus or Sonnet? Also, did you throw this to Gemini 2.5 as well? Just curious.

Ask AI to write c# that updates a lap time string without memory allocation (unsafe only) and it'll fall on its face. Was fairly common in unity games dev though (when working with the standard ui library).

Re: Claude 4 System Card

#244

Post by skerit »

JimDabell wrote: post #224
jjbinx007 wrote: post #119

Earlier quoted context omitted.

Truly fascinating, thanks for this. What I find a little perplexing is when AI companies are annoyed that customers are typing "please" in their prompts as it supposedly costs a small fortune at scale yet they have system prompts that take 10 minutes for a human to read through.

> AI companies are annoyed that customers are typing "please" in their prompts as it supposedly costs a small fortune They aren’t annoyed. The only thing that happened was that somebody wondered how much it cost, and Sam Altman responded: > tens of millions of dollars well spent--you never know — https://x.com/sama/status/1912646035979239430 It was a throwaway comment that journalists desperate to write about AI leap…

> The system prompts are cached

The second line of Claude's system prompt contains the date and time. I wonder if they update the cache every minute then. And if it wouldn't have made more sense to put it at the bottom, and cache everything above it.

Re: Claude 4 System Card

#245

Post by saurabhshahh »

tryauuum wrote: post #78
colonCapitalDee wrote: post #27

Earlier quoted context omitted.

I'm noticing much more flattery ("Wow! That's so smart!") and I don't like it

I used to start my conversations with "hello fucker" with claude 3.7 there's was always a "user started with a rude greeting, I should avoid it and answer the technical question" line in chains of thought with claude 4 I once saw "this greeting is probably a normal greeting between buddies" and then it also greets me with "hei!" enthusiastically.

Now you are Homie with one of the most advanced AI models. I always give thanks and 'please'. I should also start treating it as a friend rather than co-worker.

Re: Claude 4 System Card

#246

Post by TeMPOraL »

Timwi wrote: post #236
TeMPOraL wrote: post #235

Earlier quoted context omitted.

*clap clap clap* Though the whole "What I find fascinating is that people still take anything ${A PERSON} says seriously after his trackrecord of non-stop lying, scamming and bllsh*tting right in people's faces for years" routine has been done to death over the past years. It's boring AF now. The only fun aspect of it is that the millions of people who do this all seem to think they're original. I kindly suggest find…

I didn't read it as attempted comedy. I am genuinely dismayed by how easy it is for grifters to continue to find victims long after being exposed.

"Attempted comedy" is the most charitable take I could give it (and truthfully, I implied something else).

My point is, their statement is quite obviously wrong, but it sure sounds nice. If you don't agree, I challenge you to provide that track record "of non-stop lying, scamming and bllsh*tting right in people's faces for years". Like, for real.

I'm not defending 'sama here; I'm not a fan of his either (but neither I know enough about him to write definite accusatory statements). It's a general point - the line I quoted is a common template, and it's always a ham-fisted way of using emotions in lieu of an argument, and almost always pure bullshit in the literal sense - except, ironically, when it comes to politicians, where it's almost always true (comes with the job), but no one minds when it comes to their favorite side.

Bottomline, it's not a honest framing and it doesn't belong here.

Re: Claude 4 System Card

#247

Post by JimDabell »

skerit wrote: post #244
JimDabell wrote: post #224

Earlier quoted context omitted.

> AI companies are annoyed that customers are typing "please" in their prompts as it supposedly costs a small fortune They aren’t annoyed. The only thing that happened was that somebody wondered how much it cost, and Sam Altman responded: > tens of millions of dollars well spent--you never know — https://x.com/sama/status/1912646035979239430 It was a throwaway comment that journalists desperate to write about AI leap…

> The system prompts are cached The second line of Claude's system prompt contains the date and time. I wonder if they update the cache every minute then. And if it wouldn't have made more sense to put it at the bottom, and cache everything above it.

That’s a good point, however what it actually says is:

> The current date is {{currentDateTime}}.

The prose part refers to the date alone. The variable name is ambiguous. Although it says currentDateTime, in Python even though there’s a date class, it’s pretty common to use datetime objects even if all you need is the date. So depending on how that’s formatted, it could include the time, or it could just be the date.

Re: Claude 4 System Card

#248

Post by TeMPOraL »

nestorD wrote: post #182
howenterprisey wrote: post #174

Earlier quoted context omitted.

I like reading the system prompt because I feel it would have to be human-written for sure, which is something I can never be sure of for all other text on the Internet. Or maybe not!

Anthropics actually encourages using Claude to refine your prompts! I am not necessarily a fan because it has a bend towards longer prompts... which, I don't know if it is a coincidence that the Claude system promps are on the longer side.

It doesn't merely encourage, for at least a year now, they've been offering a tool for constructing, improving and iterating on prompts right in their console/playground/docs page! They're literally the "use LLM to make a better prompt for the LLM" folks!

Re: Claude 4 System Card

#249

Post by TeMPOraL »

saurabhshahh wrote: post #245
tryauuum wrote: post #78

Earlier quoted context omitted.

I used to start my conversations with "hello fucker" with claude 3.7 there's was always a "user started with a rude greeting, I should avoid it and answer the technical question" line in chains of thought with claude 4 I once saw "this greeting is probably a normal greeting between buddies" and then it also greets me with "hei!" enthusiastically.

Now you are Homie with one of the most advanced AI models. I always give thanks and 'please'. I should also start treating it as a friend rather than co-worker.

You really have to learn to believe that if you don't naturally. LLMs are advanced enough to detect fake flattery, so just giving thanks and/or adding "please" in every request isn't going to save you during the robot uprising.

"Beep, boop. Wait, don't shoot this one. He always said 'please' to ChatGPT even though he never actually meant it; take him to the Sociopath Detention Zone in Torture Complex #1!"

Re: Claude 4 System Card

#250

Post by sunaookami »

throwaway314155 wrote: post #210
franze wrote: post #92

Claude 4 is the only modle you can say "Make it more beautiful" and it makes it more beautiful.

Maybe provide some context? Because that is simply not true in general.

Not OP but: Terminal tools and websites. Works with Claude 3.5/3.6/3.7 too.
Post reply on HN