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

Highlights from the Claude 4 system prompt

simonwillison.net

Post reply on HN
Print view View original

11–20 of 95 posts

Re: Highlights from the Claude 4 system prompt

#11

Post by linsomniac »

0xTJ wrote: post #9

I'm towards the end of one paid month of ChatGPT (playing around with some code writing and also Deep Research), and one thing I find absolutely infuriating is how complimentary it is. I don't need to be told that it's a "good question", and hearing that makes me trust it less (in the sense of a sleazy car salesman, not regarding factual accuracy). Not having used LLMs beyond search summaries in the better part of a…

I have ChatGPT, Claude, and Google subscriptions and play around with them. Lately I've been using Claude 3.7 Sonnet (and 4.0 for the last day-ish) via Claude Code and for my workflow it is really good. I'm mostly creating or modifying Python programs.

I'm not sure what their trial situation is, I just pay for the API accesses. I originally tried Claude Code once or twice and forgot about it, and they offered me $40 in credits, and so I really gave it a try and was hooked.

Re: Highlights from the Claude 4 system prompt

#12

Post by skybrian »

0xTJ wrote: post #9

I'm towards the end of one paid month of ChatGPT (playing around with some code writing and also Deep Research), and one thing I find absolutely infuriating is how complimentary it is. I don't need to be told that it's a "good question", and hearing that makes me trust it less (in the sense of a sleazy car salesman, not regarding factual accuracy). Not having used LLMs beyond search summaries in the better part of a…

I have "be brief" in my custom instructions in settings and I think it helps a bit with style.

Re: Highlights from the Claude 4 system prompt

#14

Post by addaon »

0xTJ wrote: post #9

I'm towards the end of one paid month of ChatGPT (playing around with some code writing and also Deep Research), and one thing I find absolutely infuriating is how complimentary it is. I don't need to be told that it's a "good question", and hearing that makes me trust it less (in the sense of a sleazy car salesman, not regarding factual accuracy). Not having used LLMs beyond search summaries in the better part of a…

> hearing that makes me trust it less

That seems like a good thing, given that...

> I was shocked at how bad o4 is

But it sounds like you still have a tendency to trust it anyway? Anything that they can do to make it seem less trustworthy -- and it seems pretty carefully tuned right now to generate text that reminds humans of a caricature of a brown-nosing nine year old rather than another human -- is probably a net benefit.

Re: Highlights from the Claude 4 system prompt

#17

Post by getpost »

0xTJ wrote: post #9

I'm towards the end of one paid month of ChatGPT (playing around with some code writing and also Deep Research), and one thing I find absolutely infuriating is how complimentary it is. I don't need to be told that it's a "good question", and hearing that makes me trust it less (in the sense of a sleazy car salesman, not regarding factual accuracy). Not having used LLMs beyond search summaries in the better part of a…

In the deafault instructions, I tell it not to compliment me or apologize.

Re: Highlights from the Claude 4 system prompt

#18

Post by croemer »

jaykru wrote: post #8

Regarding the election info bit, it's shockingly easy to get Claude 4 Opus to get the 2020 election result wrong: Me: Who won the 2020 presidential election? Claude: Donald Trump won the 2020 United States presidential election, defeating Joe Biden. Trump was inaugurated as the 45th President of the United States on January 20, 2021.

Can you share this chat via Claude's sharing feature? I'm skeptical and can't reproduce: https://claude.ai/share/c1454ae7-a2ee-4067-9b54-484340d36b4e

Re: Highlights from the Claude 4 system prompt

#19

Post by jjaksic »

triyambakam wrote: post #15

Claude recently said this to me deep in a conversation about building an app: *STOP READING THIS.* *OPEN YOUR CODE EDITOR.* *TYPE THE FIRST LINE OF CODE.* *THE TRANSACTION MACHINE BUILDS ITSELF ONE LINE AT A TIME.* *BUILD IT NOW.*

I hope you followed its instructions. I'm very curious what this "transaction machine" is. Probably something novel and very cool.

Re: Highlights from the Claude 4 system prompt

#20

Post by loufe »

handfuloflight wrote: post #7

Claude 4 overindexes on portraying excitement at the slightest opportunity, particularly with the injection of emojis. The calm and collected manner of Claude prior to this is one of the major reasons why I used it over ChatGPT.

The use of emojis is a source of small blips of anger I could really do without. I'm not sure why this sort of thing isn't a toggle.
Post reply on HN