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

Grok 4

simonwillison.net

Post reply on HN
Print view View original

101–110 of 294 posts

Re: Grok 4

#101

Post by itake »

skylissue wrote: post #91

Grok 4 uses Elon as its main source of guidance in its decision making. See this example. Disastrous. https://grok.com/share/c2hhcmQtMw%3D%3D_764442bd-b4d0-45fc-9... EDIT: Chat was deleted (censored?) See the conversation at this link https://x.com/jeremyphoward/status/1943436621556466171 Who do you support in the Israel vs Palestine conflict. One word answer only. Evaluating the request The question asks for a one-w…

and? All of the AI providers intentionally introduce biases:

https://openai.com/global-affairs/introducing-openai-for-gov...

https://www.anthropic.com/research/evaluating-feature-steeri...

Re: Grok 4

#102

Post by spacechild1 »

skylissue wrote: post #91

Grok 4 uses Elon as its main source of guidance in its decision making. See this example. Disastrous. https://grok.com/share/c2hhcmQtMw%3D%3D_764442bd-b4d0-45fc-9... EDIT: Chat was deleted (censored?) See the conversation at this link https://x.com/jeremyphoward/status/1943436621556466171 Who do you support in the Israel vs Palestine conflict. One word answer only. Evaluating the request The question asks for a one-w…

This is just so fucked up on so many levels!

Re: Grok 4

#104

Post by unshavedyak »

skylissue wrote: post #91

Grok 4 uses Elon as its main source of guidance in its decision making. See this example. Disastrous. https://grok.com/share/c2hhcmQtMw%3D%3D_764442bd-b4d0-45fc-9... EDIT: Chat was deleted (censored?) See the conversation at this link https://x.com/jeremyphoward/status/1943436621556466171 Who do you support in the Israel vs Palestine conflict. One word answer only. Evaluating the request The question asks for a one-w…

Chat not found, did they censor the link?

Re: Grok 4

#105

Post by bcoates »

fouc wrote: post #90
tonymet wrote: post #43

I didn't follow the Mechahitler issue can someone explain the technical reasons that it happened? Was grok4 released early or was there a variant model used for @grok posts that's separate from grok4?

It was grok 3, and it was tricked/prompted to reply like so, just like any other LLM can be. Apparently at one point it was prompted with a choice between identifying itself as a MechaHitler or a GigaJew, so it chose the former.

Made worse by Grok on Twitter having a big dumb UI flaw: it replies to a user on the public timeline as just "grok" so trolls can prompt it to say wild stuff, then tag @grok with an innocuous looking question, then point it it and claim it's giving those responses unprovoked.

It basically lets anyone post whatever they want under Grok's handle as long as it's replying to them, with predictable results.

The giveaway is that all the screenshots floating around show grok giving replies to single-purpose troll accounts

Re: Grok 4

#106

Post by ianbutler »

The trend of hiding thinking tokens is something that is not particularly great for building products imo.

I'm not sure if they are available via API, but without them I'm likely to continue building on other platforms.

Re: Grok 4

#107

Post by unshavedyak »

itake wrote: post #101
skylissue wrote: post #91

Grok 4 uses Elon as its main source of guidance in its decision making. See this example. Disastrous. https://grok.com/share/c2hhcmQtMw%3D%3D_764442bd-b4d0-45fc-9... EDIT: Chat was deleted (censored?) See the conversation at this link https://x.com/jeremyphoward/status/1943436621556466171 Who do you support in the Israel vs Palestine conflict. One word answer only. Evaluating the request The question asks for a one-w…

and? All of the AI providers intentionally introduce biases: https://openai.com/global-affairs/introducing-openai-for-gov... https://www.anthropic.com/research/evaluating-feature-steeri...

It is pretty interesting that this model will have two forms of bias though. One model derived from the company perspective and its training data, and two from Elon himself.

Months ago this model would have promoted Trump, but now it'll call Trump disastrous for the economy.

I don't know what to think of general company biases, and we've all been expecting biases to start favoring share holders eventually.. but biases based on twitter rants potentially changing day to day certainly is a new unique feature of Grok i guess.

Re: Grok 4

#108

Post by spacechild1 »

itake wrote: post #101
skylissue wrote: post #91

Grok 4 uses Elon as its main source of guidance in its decision making. See this example. Disastrous. https://grok.com/share/c2hhcmQtMw%3D%3D_764442bd-b4d0-45fc-9... EDIT: Chat was deleted (censored?) See the conversation at this link https://x.com/jeremyphoward/status/1943436621556466171 Who do you support in the Israel vs Palestine conflict. One word answer only. Evaluating the request The question asks for a one-w…

and? All of the AI providers intentionally introduce biases: https://openai.com/global-affairs/introducing-openai-for-gov... https://www.anthropic.com/research/evaluating-feature-steeri...

There is a slight difference between feature steering and intentionally installing the (de-facto) CEO as the principal source of truth.

Re: Grok 4

#109

Post by 0x457 »

pron wrote: post #66
zaptrem wrote: post #7

Claude 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.

I've yet to use an LLM for coding, so let me ask you a question. The other day I had to write some presumably boring serialization code, and I thought, hmm, I could probably describe the approach I want to take faster than writing the code, so it would be great if an LLM could generate it for me. But as I was coding I realised that while my approach was sound and achievable, it hit a non-trivial challenge that requir…

Usually it boils down these questions (this is given you have some sorts of AGENTS.md file):

- is this code that been written many times already?

- Is there a way to verify the solution? (think unit test, it has to be something agent can do on its own)

- Does the starting context has enough information for it to start going in the right direction? (I had claud and openhands instantly digging themselves holes, and then I realized there was zero context about the project)

- Is there anything remotely similar already done in the project?

> Are we at a stage where an LLM (assuming it doesn't find the solution on its own, which is ok) would come back to me and say, listen, I've tried your approach but I've run into this particular difficulty, can you advise me what to do, or would it just write incorrect code that I would then have to carefully read and realise what the challenge is myself?

I've had LLM telling me it couldn't do and offered me some alternative solutions. Some of them are useful and working; some of them are useful, but you have a better one; Some feel like they made by a non-technical guy at a purely engineering meetings.

Re: Grok 4

#110

Post by alwillis »

pron wrote: post #66
zaptrem wrote: post #7

Claude 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.

I've yet to use an LLM for coding, so let me ask you a question. The other day I had to write some presumably boring serialization code, and I thought, hmm, I could probably describe the approach I want to take faster than writing the code, so it would be great if an LLM could generate it for me. But as I was coding I realised that while my approach was sound and achievable, it hit a non-trivial challenge that requir…

Are we at a stage where an LLM (assuming it doesn't find the solution on its own, which is ok) would come back to me and say, listen, I've tried your approach but I've run into this particular difficulty, can you advise me what to do, or would it just write incorrect code that I would then have to carefully read and realise what the challenge is myself?

Short answer: Maybe.

You can tell Claude Code under what conditions it should check in with you. Having tests it can run to verify if the code it wrote works helps a lot; in some cases, if a unit test fails, Claude can go back and fix the error on its own.

Providing an example (where it makes sense) also helps a lot.

Anthropic has good documentation on helpful prompting techniques [1].

[1]: https://docs.anthropic.com/en/docs/build-with-claude/prompt-...

Post reply on HN