dimgl

In short: no.

Nothing comes close, in my opinion. Sonnet and Opus are still the best models. The Codex variants of the GPT models are also great. I've tried MiniMax, GLM, Qwen and Kimi and for anything even remotely complex these models seriously struggle.

Is this spam? It's incomprehensible.

I doubt it's this. This was an `npm` misconfiguration.

Thank you. Yes, I'm going to refrain from airing out my dirty laundry. I made a bad decision, now I'm living with it, and more context doesn't actually change the intent behind my message: these tools are dangerous. Getting better, but still dangerous.

Even as someone who (wrongly) believed that I had high emotional intelligence, I too was bit by this. Almost a year ago when LLMs were starting to become more ubiquitous and powerful I discussed a big life/professional decision with an LLM over the course of many months. I took its recommendation. Ultimately it turned out to be the wrong decision.

Thankfully it was recoverable, but it really sobered me up on LLMs. The fault is on me, to be clear, as LLMs are just a tool. The issue is that lots of LLMs try to come across as interpersonal and friendly, which lulls users into a false sense of security. So I don't know what my trajectory would have been if I were a teenager with these powerful tools.

I do think that the LLMs have gotten much better at this, especially Claude, and will often push back on bad choices. But my opinion of LLMs has forever changed. I wonder how many other terrible choices people have made because these tools convinced them to make a bad decision.

Agreed, I have not been impressed with Kagi at all.

None exist yet, but that doesn't mean OpenCode is automatically good.

Yeah this looks like OpenCode. I've never gotten good results with it. Wild that it has 120k stars on GitHub.

Twitter.

Are you based in the U.S.?

Unfortunately... I want to mirror this sentiment. I interviewed a lot of candidates (and worked with many teammates) in my last few roles and I saw some pretty worrying trends...

I actually had to do this exact thing with my game recently in order to create interesting AI patterns during combat.

The only way this happens is if models that are specifically made to do certain kinds of coding start to exist. Then this would start to become an issue, yes, until those models are distilled into smaller models.

You mean 35B A3B? If this is shit, this is some of the best shit out I've seen yet. Never in a million years did I think I'd have an LLM running locally, actually writing code on my behalf. Accurately too.

I'm using Qwen 3.5 27b on my 4090 and let me tell you. This is the first time I am seriously blown away by coding performance on a local model. They are almost always unusable. Not this time though...

That's funny. I wrote a blog post about something very similar.

https://dextermiguel.com/posts/codex-helped-me-recover-lost-...

What do you do now?

Pretty sure this entire comment is AI generated.

I'm really considering it

> The build.bat above isn’t just a helper script; it’s a declaration of independence from the Visual Studio Installer.

I am so fed up with this! Please if you're writing an article using LLMs stop writing like this!

My personal favorite: That’s not a threat. It’s free R&D.

I was enjoying the article, and then the author hit me with one of these:

> AI didn't just repeat the mistake. It broke the mistake open.

Come on bruh

Good post. I'd argue this is very similar to solo game development. There's a lot of extra administrative stuff that simply has nothing to do with actually making games and a lot more to do with making a real business. So the framing there is accurate.

> it's hard not to think we're living the last decades of American economic hegemony

Bit of a stretch to correlate this with Instagram suspending some guy

Actually, LLM fiction writing is awfully bad. But it does help with ideas!

I'm trying my hardest to make it feel high quality instead of just slop.

I'm building all of the systems with LLMs and using LLMs to fast track the creation of content such as storylines, characters, etc. All of the assets are mostly bought and created by me.

I'm building an entire game on Unity using LLMs. It's an action RPG.

Did you get those backwards? Codex, Gemini, etc. all wait until the requests are done to accept user feedback. Claude Code allows you to insert messages in between turns.

20 years ago was 2006? Oh no...

SSD-native RDBMS sounds good in theory! What's in mean in practice? What relational databases are simpler and more performant? Point me in their direction!