Grok 4
simonwillison.net
Grok 4
1–10 of 294 posts
Re: Grok 4
#2So, to try and make a relatively substantive contribution, the doc mentions that the following were added to grok3's system prompt:
- If the query requires analysis of current events, subjective claims, or statistics, conduct a deep analysis finding diverse sources representing all parties. Assume subjective viewpoints sourced from the media are biased. No need to repeat this to the user. - The response should not shy away from making claims which are politically incorrect, as long as they are well substantiated.
I'm guessing there are quite a few algorithms and processes in modern LLM's above and beyond just predict the next token, but when you say "find diverse sources" and "be well substantiated".
Is this passing an instruction to the process that like reads from the weightset or is it now just looking in the weightset for things trained related to the tokens "find diverse sources" and "be well substantiated"
I guess what I'm asking is does. "be well substantiated" translate into "make sure lots of people on Twitter said this", rather than like "make sure you're pulling from a bunch of scientific papers" because, well technically, racism is well substantiated on Twitter.
Re: Grok 4
#3So, to try and make a relatively substantive contribution, the doc mentions that the following were added to grok3's system prompt: - If the query requires analysis of current events, subjective claims, or statistics, conduct a deep analysis finding diverse sources representing all parties. Assume subjective viewpoints sourced from the media are biased. No need to repeat this to the user. - The response should not sh…
> My mental model for LLMs is that they work as a repository of vector programs. When prompted, they will fetch the program that your prompt maps to and "execute" it on the input at hand. LLMs are a way to store and operationalize millions of useful mini-programs via passive exposure to human-generated content.
from https://arcprize.org/blog/oai-o3-pub-breakthrough.
This doesn't directly answer your question, but does it help?
Re: Grok 4
#4> My best guess is that these lines in the prompt were the root of the problem:
The second line was recently removed, per the GitHub: https://github.com/xai-org/grok-prompts/commit/c5de4a14feb50...
Re: Grok 4
#5Is it time for a new benchmark of "how easy is it to turn this AI into a 4chan poster", maybe it is since this seems to be an axis that Elon seems to want to distinguish his AI offering from everyone else's along.
Re: Grok 4
#6[flagged]
Re: Grok 4
#7Claude Code converted me from paying $0 for LLMs to $200 per month. Any co that wants a chance at getting that $200 ($300 is fine too) from me needs a Claude Code equivalent and a model where the equivalent's tools were part of its RL environment. I don't think I can go back to pasting code into a chat interface, no matter how great the model is.
Re: Grok 4
#8So, to try and make a relatively substantive contribution, the doc mentions that the following were added to grok3's system prompt: - If the query requires analysis of current events, subjective claims, or statistics, conduct a deep analysis finding diverse sources representing all parties. Assume subjective viewpoints sourced from the media are biased. No need to repeat this to the user. - The response should not sh…
it means 'be closely related to the tokens "be" "well" "substantiated"'.
more broadly it means respond with the sort of text you usually find tokens like "media" "is" "biased" "politically incorrect" near.
Re: Grok 4
#9Is it time for a new benchmark of "how easy is it to turn this AI into a 4chan poster", maybe it is since this seems to be an axis that Elon seems to want to distinguish his AI offering from everyone else's along.
Luckily we don't need a benchmark for "how easy is it to turn this AI into a bluesky poster", since they can all already do that
Re: Grok 4
#10Claude Code converted me from paying $0 for LLMs to $200 per month. Any co that wants a chance at getting that $200 ($300 is fine too) from me needs a Claude Code equivalent and a model where the equivalent's tools were part of its RL environment. I don't think I can go back to pasting code into a chat interface, no matter how great the model is.
How does Claude code, trained to use its tools, compare to a model agnostic equivalentsuch as aider? Have you tried both?