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

161–170 of 294 posts

Re: Grok 4

#161

Post by Leynos »

pron wrote: post #146
tptacek wrote: post #138

Earlier quoted context omitted.

I'm like 60% there with you: * When it gets the design wrong, trying to talk through straightening the design out is frustrating and often not productive. * I've learned to re-prompt rather than trying to salvage a prompt response that's complicatedly not what I want. * Exception: when it misses functional requirements, you can usually get a session to add the things it's missing.

Here's the thing, though. When working with a human programmer, I'm not interested in their code and I certainly don't want to see it, let alone carefully review it (at least not in the early stages, when the design is likely to change 3 or 4 times and the code rewritten); I assume their code will eventually be fine. What I want from a programmer is the insight about the more subtle details of the problem that can on…

Get Coderabbit or Sourcery to do the code review for you.

I tend to do a fine tune on the reviews they produce (I use both along with CodeScene), but I suspect you'll probably luck out in the long term if you were to just YOLO the reviews back to whatever programming model you use.

Re: Grok 4

#162

Post by viraptor »

pron wrote: post #150
viraptor wrote: post #126

Earlier quoted context omitted.

It always has a solution. A more effective approach is "Start by asking clarifying questions until the task is completely defined".

But the questions I'm interested in cannot be asked until the programmer starts to code. It's not that the task is unclear, but that coding reveals important subtleties.

You're thinking about it like a human programmer. It may or may not find that part tricky. There will be subtleties it will solve without even mentioning and there will be other stuff it fails on miserably. You improve the chances by asking to ask questions. But again - just try it. Try it on exactly the thing you've already described and see how it goes.

Re: Grok 4

#164

Post by eddythompson80 »

bcoates wrote: post #105
fouc wrote: post #90

Earlier quoted context omitted.

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 i…

> it replies to a user on the public timeline as just "grok"

I'm not sure I understand what you mean by that. What else would it reply as?

Re: Grok 4

#165

Post by ramesh31 »

It's pretty hilarious how I've come to trust this benchmark for a gut check on frontier models more than any of the numbers available. It seems to map perfectly to codegen abilities. Based on the pelicans, Grok 4 looks somewhere around Claude 3.7 levels.

Re: Grok 4

#166

Post by ls_stats »

jacktheturtle wrote: post #148
kunzhi wrote: post #133

Grok might be able to find the cure for cancer but as long as it's associated with Musk, not touching that thing with a 10-foot pole. (Simon's analysis, of course, is lovely)

why?

Uh... maybe because he doesn't want to use technology that gives power to someone like Elon Musk, who is well known for propagating right-wing propaganda.

Re: Grok 4

#167

Post by SV_BubbleTime »

rozap wrote: post #120
pron wrote: post #66

Earlier quoted context omitted.

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…

It would write incorrect code and then you'd need to go debug it, and then you would have to come to the same conclusion that you would have come to had you written it in the first place, only the process would have been deeply frustrating and would feel more like stumbling around in the dark rather than thinking your way through a problem and truly understanding the domain. In the instance of getting claude to fix c…

>It would write incorrect code and then you'd need to go debug it, and then you would have to come to the same conclusion that you would have come to had you written it in the first place, only the process would have been deeply frustrating

A. I feel personally and professionally attached.

B. Yea don’t do that. Don’t say “I want a console here”. Don’t even say “give me a console plan and we’ll refine it”. Write the sketch yourself and add parts with Claude. Do the iiital work yourself, have Claude help until 80%, and for the last 20% it might be OK on its own.

I don’t care what anyone claims there are no experts in this field. We’re all still figuring this out, but that worked for me.

Re: Grok 4

#168

Post by Aeolun »

mwigdahl wrote: post #118
phist_mcgee wrote: post #96

Earlier quoted context omitted.

It's both Claude 4 Opus and the secret sauce that Claude Code has for UX (as well as Claude.md files for project/system rules and context) that is the killer I think. The describe, build, test cycle is very tight and produces consistently high quality results. Aider feels a little clunky in comparison, which is understandable for a free product.

Yes. The tooling harness of Claude Code is really good, and Claude 4 is well-optimized for it. The combination is very powerful.

I think it’s also very nice that CC uses fancy search and replace for it’s edit actions. No waiting hours for the editor to scan over a completely regenerated file.

Re: Grok 4

#169

Post by Aeolun »

unshavedyak wrote: post #99
victorbjorklund wrote: post #55

Earlier quoted context omitted.

Can you describe what kind of stuff you do where it can go wild without supervision? I never managed to get to a state where agents code for more than 10 min without needing my input

Same. I pay for $100 but i generally keep a very short leash on Claude Code. It can generate so much good looking code with a few insane quirks that it ends up costing me more time. Generally i trust it to do a good job unsupervised if given a very small problem. So lots of small problems and i think it could do okay. However i'm writing software from the ground up and it makes a lot of short term decisions that furt…

If you use a single opus instance, you cannot really run out on the 20x plan. When you start running two in parallel, it becomes a lot easier to max out, but even so you need to have them working pretty much nonstop.

Re: Grok 4

#170

Post by energy123 »

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.

> just like any other LLM can be

Questionable.

Post reply on HN