Live data from Hacker News

DeepSeek V4 – almost on the frontier

simonwillison.net

221–230 of 420 posts

Re: DeepSeek V4 – almost on the frontier

#221
post #113

The biggest differentiator for me: DeepSeek just does what I ask. I've tried using both GPT and Claude for reverse engineering recently, both refused. I even got a warning on my OpenAI account.

Speaking of this: is anyone working on binary to source decompiler models? Seems like a no brainer and I could see it working exceptionally well especially if they were fine tuned for each language. So if you can tell it’s a Go binary use a Go model, etc.

Re: DeepSeek V4 – almost on the frontier

#222
post #3

I've been using v4 pro for the past few days and honestly in terms of quality it seems more or less on par with open AIs 5.4 or opus 4.6 (i havent tried 4.7) To be clear, i'm not doing state of the art stuff. I mostly used it for frontend development since i'm not great at that and just need a decent looking prototype. But for my purposes it's a perfectly good model, and the price is decent. I can't wait for open mod…

You can use Tinfoil for inference, which lets you use the model in the cloud while getting similar privacy as running locally: https://tinfoil.sh/inference . Disclaimer I'm the cofounder. This works by running the model inside a secure enclave (using NVIDIA confidential computing) and verifying the open source code running inside the enclave matches the runtime attestation. The docs walk you through the verification…

Worth noting that NVIDIA confidential computing and similar schemes have been compromised and shouldn't be relied upon if it really matters. See https://tee.fail/ and similar.

Re: DeepSeek V4 – almost on the frontier

#223
In my experience V4 is pretty good but for very hard problems it burns way too many tokens that it ends up being not so cheap anymore. I'm working on a compiler and the tasks are very involved. Tests won't pass unless it gets it absolutely right. 5.5 can achieve more in less time compared to V4 for me.

Re: DeepSeek V4 – almost on the frontier

#224

Earlier quoted context omitted.

Are you kidding? Ask this question and see what answer you get: What famous photo depicts a man standing in front of a line of tanks?

Huh? Did you ever actually ask v4 this question?

I tried after reading parent, and the DeepSeek app refused and suggested to switch topics. I don‘t know if the chat interface uses v4, though.

Re: DeepSeek V4 – almost on the frontier

#225
post #221
post #113

The biggest differentiator for me: DeepSeek just does what I ask. I've tried using both GPT and Claude for reverse engineering recently, both refused. I even got a warning on my OpenAI account.

Speaking of this: is anyone working on binary to source decompiler models? Seems like a no brainer and I could see it working exceptionally well especially if they were fine tuned for each language. So if you can tell it’s a Go binary use a Go model, etc.

Trivially easy to train if it doesn’t exist already. Take a codebase, compile it to binary, train a model to reverse the process since you have the ground truth.

Re: DeepSeek V4 – almost on the frontier

#226
post #113

The biggest differentiator for me: DeepSeek just does what I ask. I've tried using both GPT and Claude for reverse engineering recently, both refused. I even got a warning on my OpenAI account.

> I even got a warning on my OpenAI account. This idea of software threatening the user with consequences is totally wild and dystopian. Fellow developers, what kind of world have be built? This is insanity. Imagine if my hammer told me, "Hey, you shouldn't use me on screws--only nails. Do it again and I'll self-destruct!" WTF people, stop making this kind of software!

I think it's closer to asking a remote (human) assistant to do something that someone doesn't want done (e.g., view the source of a closed-source product, whether through reverse engineering, going into their office, or social engineering) and that remote assistant company saying, "Please stop asking our assistants to do that."

You can still use an IDE (hammer) to reverse engineer anything you want.

Re: DeepSeek V4 – almost on the frontier

#227
post #49

Earlier quoted context omitted.

How did you use it? OpenRouter, or provider directly?

I'm guessing downvoted because OpenRouter was mentioned in the note (which may not have been there originally), but aside from that this is a perfectly legitimate question. In order to reproduce we need to know how. Was it a coding agent like opencode, an IDE, or something else?

OpenCode + Direct Deepseek API.

Re: DeepSeek V4 – almost on the frontier

#228
post #113

The biggest differentiator for me: DeepSeek just does what I ask. I've tried using both GPT and Claude for reverse engineering recently, both refused. I even got a warning on my OpenAI account.

> I even got a warning on my OpenAI account. This idea of software threatening the user with consequences is totally wild and dystopian. Fellow developers, what kind of world have be built? This is insanity. Imagine if my hammer told me, "Hey, you shouldn't use me on screws--only nails. Do it again and I'll self-destruct!" WTF people, stop making this kind of software!

> This idea of software threatening the user with consequences is totally wild and dystopian.

This idea of software built on top of reverse-engineered data threatening the user with consequences is what's really even wild and dystopian.

Re: DeepSeek V4 – almost on the frontier

#229
post #113

The biggest differentiator for me: DeepSeek just does what I ask. I've tried using both GPT and Claude for reverse engineering recently, both refused. I even got a warning on my OpenAI account.

Are you kidding? Ask this question and see what answer you get: What famous photo depicts a man standing in front of a line of tanks?

Are you really concerned about asking these kinds of questions though? Like how many LLM-able Tiananmen Square questions are you needing answered per month really? And it seems like you know not to trust it, so there's not even a risk that you're going to ask such a question and rely on the answer.

I run into Claude being a stubborn idiot about far more useful stuff all the time. And often all it takes to bypass is starting a new chat and reframing it, so it's entirely pointless hand wringing.

Then let's not forget only one of these is a paid product, and it's not the more annoying one. I feel like I can forgive DeepSeek for just obeying the laws of the country they're based in, as silly as those might be, because they're being pretty generous with the weights in the first place.

Re: DeepSeek V4 – almost on the frontier

#230
post #113

The biggest differentiator for me: DeepSeek just does what I ask. I've tried using both GPT and Claude for reverse engineering recently, both refused. I even got a warning on my OpenAI account.

In my experience GLM 5.1 has been excellent when paired with IDA Pro (DeepSeek v4 pro comes in close second, Kimi straight up refuses). Claude can only do reverse engineering if you throw it into some sort of hero/saviour mode then gradually pivot into red team (though it gets easily tripped).
Post reply on HN