But doesn't it hallucinate a lot? Does that affect your workflow?

It hallucinates plenty, about the same as Codex models and all other LLMs! I review all code it writes, thoroughly, check the test coverage, write tests myself, have other models/chats cross-check the work with a review skill (which I've shared in another comment in this thread).

Usually unreviewed code only gets committed if I really don't care, like for one-off scripts, which I sandbox with github.com/lionkor/sbh or run as an unprivileged user.

its quality is not great, and neither are most llms.

Aside from what squidbeak already said, I have to say the quality varies a lot, and goes above the "good" threshold enough times that using these models is worth the time and effort. Compared to something like GPT-5.4 to GPT-5.6 Codex models, they cost 50-100x less (fifty to one hundred TIMES less), and can do most annoying or well-specified tasks just as well.

The main difference is that deepseek is bad at prose, and Codex models are much more eager to use tools provided to them (which is usually fine, they often make like 3 todos via tool calls for a simple one step task which is silly though), and deepseek in general benefits from good instructions more than GPT models maybe do.

Deepseek becomes much better if you give it tools for asking clarifying questions, doing self-review with subagents, and so on. The more tools it uses, the better the signal-to-noise ratio in its context, and the more consistent the output.

You must still review 100% of the code as if it's trying to sell you insurance.

I love deepseek's (Pro) writing. I feel it's more nuanced and natural.

An experienced software engineer (read his profile) praises the value he's found in Deepseek, and gives some real data showing how affordable that value is.

Then you, dakolli - out of generosity and minute-to-minute devotion to enlightenment - sacrifice time from your busy day to sit down (though perhaps that's been painful lately?) or stand up with your phone - and offer a profound, deeply thought-out counterpoint in the following form (and I'll paraphrase):

"Nah mate, it's shit. All LLMs are shit."

How one is affected psychologically by LLMs 'hallucinating' presumably closely tracks how one is affected by pathological liars. Most of the things pathological liars say is true and if you can put up with it, one can work with them and learn from them. But some respond with extreme hatred and avoidance. This seems like one of the responses that is reasonable ... as is acceptance and instrumentalization of the individual.

Among countless other experienced engineers... The cognitive dissonance here is frightening.

His Bio: c++, rust and c#, software engineer located in Germany, currently working in the electrical power industry (high- to ultra high voltage testing- and measurement equipment).

The stories I could tell you about people who would have that exact bio. I work adjacent to this industry, I promise you there are thousands of people with these exact credentials who are extremely bad engineers. Also, I'm not sure why having something in your bio makes you qualified.. You llm people have completely fried your brains.

Sorry, I use these tools every single day, a lot, I'm not speaking from a lack of exposure, but these llms are terrible and all they do is add massive amounts of slop to your code. Yes they're useful for when you want to be lazy, or you're doing something not serious, or for the people who want to be lazy all the time (most llm proponents). Have fun making your competency tied to the quality and quantity of tokens you have access to slopper.

I really can't begin to describe how stupid I think you are for thinking that having that statement in your bio makes you a qualified engineer.

I agree a bio is a bad proxy, and I'm not saying I'm amazing but I'm not THAT incompetent. Most of my GitHub is pre-LLM era; github.com/lionkor

Edit: And like a lot of tools, HOW you use them is just about as important as the quality of the tool itself. Of course the tools can produce massive amounts of bad quality slop, they can also produce fast, focused edits that make sense.

I'm not even trying to call you out, I'm sure you're solid.

Oh I know, I'm just trying to say that I agree fully that a bio is a terrible proxy, while also showing what I think is a good proxy for skill (open source work before LLMs became this "good", for example). I'm a big proponent of show, don't tell, and LLMs have kind of ruined this.

> I really can't begin to describe how stupid I think you are for thinking that having that statement in your bio makes you a qualified engineer.

Well, I guess having "Two PhDs, Three masters degrees. Expert in everything.." in your bio makes you very smart!

Look at his history -- he's just here to shitpost. Flag and move on.

For doing what?

everything.

Maybe it’s just your ability to use the tool and other people more proficient in using the tool are actually getting reasonable results from it.

There's a small relief in knowing that these junk comments are at least not AI generated (in all likelihood.)

What harness are you using to achieve that level of token caching?

I use pi, and, like the sibling comment, the caching ratio is fantastic. I work on C#, Rust, C, C++, shell scripting, and other areas.

I'm using pi and my caching is ~99%.

Can you give more info on how you use/prompt those LLMs for code review and what kind of prompts you use?

I've had worse experiences doing it because the quality of answer has been quite bad, and I'm wondering if my methods are the reason.

Yes, gladly! I have not yet open-sourced my skills etc., but I can give some insight and share a couple here.

Review is a skill, as in, a SKILL.md with a folder full of references:

- SKILL.md: https://gist.github.com/lionkor/161525be858d1d75db4c13c0f093...

- references/output-contract.md: https://gist.github.com/lionkor/8c68e33becef7a21f8408c7dc119...

- references/review-lenses.md: https://gist.github.com/lionkor/0a8b080fe45306213efddf3ebb75...

- references/review-workflow.md: https://gist.github.com/lionkor/d2d374b133ceb7e3660bd530ee72...

- references/section-rules.md: https://gist.github.com/lionkor/8a9e503adc7fd3697410cf021f27...

I'm aware that almost all of this is prompt voodoo, and there's no guarantee for the review to find anything or everything, but making it a dedicated skill and thoroughly observing the output thinking, tool calls, and result, lets me adjust these over time and fill the weak spots with even more prompting.

I use this skill by simply telling the agent something like "Review the changes on the current branch against origin/main, take special care with backwards-incompatible changes to the public API" or something like that.

I use `pi` (pi.dev) with a subagents extension, so that I can ask the agent to invoke a subagent to do the review, on work that the agent did.

For models, I use the highest possible reasoning on whatever model I feel like makes sense, usually this is GPT-5.5 or deepseek flash/pro, depending on the confidentiality of the codebase, on the highest reasoning always (for reviews).

I've also had success with a review checklist, though it doesn't produce an easy to parse (for humans) output: https://gist.github.com/lionkor/054ac2cf241e0765eee2383f0dba...

This is why my review skill mandates a very strict output contract. I need the output to be very easy to parse, and the output contract I've specified there does that.

In general I let <whatever the latest model of OpenAI's ChatGPT is> author and review SKILL.md and similar large prompts, usually with a ruleset like this, which is a 1600 line research artifact from a long GPT 5.5 "Pro" research session on prompt engineering: https://gist.github.com/lionkor/71498794d0a7d72173fc58766f25...

Does the review catch all issues? Not at all. Does it catch, usually more than one, important issue, across large changesets? Absolutely, and that's the point! :)

Feel free to ask me any questions, I'm also happy to share more about my setup via email or add you or anyone else to my private repos with more of these.

Thanks for sharing.

Which languages are the reviews most successful on in your work so far? Im assumining js/python , would a similar output be feasible on lower level c++ or C#/Java.

No js or python, it's mostly C#, Rust, and C++. They're helpful/useful on all of those, I've also used the review skill on shell scripts, GitLab pipelines, Powershell scripts, C, and a couple other odd things. It's almost never useless to run it on something, it usually finds things, even if they're sometimes not very major.

OpenRouter?

No, platform.deepseek.com for me! The caching is super important, not sure how open router performs, I haven't tried it.

Works out of the box with OpenRouter for most models. Some providers are a bit flaky, but DeekSeek (provider) has been one of the most reliable for me, no problems hitting >99% CH.

The problem is when OpenRouter switches providers..

That's fair, each provider maintains their own cache. OpenRouter does make an effort to keep providers "sticky", but it may hop/stick to another if latency is too high.

If you don't care about latency, you can create a preset with a single provider, then use that as the model key (i.e. `@preset/deekseek-v4-excl`). The only real downside is OpenRouter's service fee. If you don't want the convenience of switching models, or their excellent dashboard, it's definitely better to pay the provider directly.

You are using DeepSeek's services directly? Doesn't that end up sending at least snippets/chunks of code to a server where it is subject to Chinese government data access laws? Even if I was okay with that, my organization would never be. And even if they were, our partners/vendors/customers would not be. I think that's the sticking point for a lot of people.

Yes all of it goes straight to China! All of it is also open source or source available, or will be in the future. The stuff that isn't is trivial enough.

For any work with protected intellectual property, I use other providers, for the contractual guarantees, but I think it would be silly to think that OpenAI or Anthropic are not training on literally all data they get. How could you ever tell if they did? They can just claim the data was mislabelled, or ignore the accusations. If you have serious IP, use only local models.

So go with some other provider who hosts the models like OpenRouter if are worried about this.

Some employers have a policy prohibiting any use of Chinese models, not even allowed to run them locally on air-gapped machines.

That's just paranoid, might as well argue that the models will sap an impurify all of our precious bodily fluids.

I agree it's absurd. I was just commenting on the bit about organizations not allowing it.

DeepSeek is amazing, they are, from a cost/benefit literally an order of magnitude or more better than the 'SOTA' models, and yet no one really talks about them.

I'm using them for my micro-saas, and they have made my niche economically profitable where as SOTA models are only slightly better for massively increased expense. Its truly impressive.

Word of advice to anyone, not all your use of LLM tech needs to be code/dev work related.

We are entering 'Web 4.0 era' or whatever you want to call it. Massive transformations of nearly every single business will and are being developed as the cost of intelligence as a commodity is falling through the floor...

Those are rookie numbers. Last 13 days including today, so effectively 12 days of usage:

- $19.27 USD - API requests: 7,877 - Tokens: 2,116,598,952

Ok this is a bit of lie, a lot of my tasks are very experimental loops whose 99% output is like rubbish and can work forever continuously and take advantage of that 120x cheaper input cache. Still incredible.

What are the tasks where it falls short?