This weekend I programmed a matrix bot with encryption and a Rust agent with some tools. Because I need one and OpenClaw just felt... not what I wanted. Two days later and 20 dollars poorer I have what I need: a multimodal agent written in rust that has access to my homelab.

Nothing felt off with GLM. It did what I wanted, was fast, had a decent not very annoying personality and was much cheaper than Opus or GPT.

I used it unquantized through Fireworks, but there are multiple other providers too.

https://swelljoe.com/post/will-it-mythos/

Also of note, I found giving models access to the open source semgrep as a tool makes some perform worse and none perform better, though it's plausible there's a way to wire it up in a harness that presents useful information to the model without the model having to know how to use it (my theory is that semgrep isn't heavily represented in the training data, so you're asking the model to do two things at once: figure out how to use semgrep and find security bugs, and both tasks suffer for the lack of focus...most small models, and some big models, can't do that well).

Edit: But, also, more testing is ongoing. I suspect GLM 5.2 will also be a consistently strong performer. It seems to excel at most things I've tested on it.

[1] https://huggingface.co/zai-org/GLM-5.2

GLM 5.2 is already capable enough to assist in self-training which is similar to what we saw happen with frontier models and they appear to be getting there at a significantly lower cost than openai/anthropic.

I have a feeling Anthropic may still come out cheeper (mainly thanks to enterprises subsidising the Max subscriptions).

But I'm very excited with the possibility of using fully EU based inference rivalling Opus in quality.

In general, it's comparable across the board. Claude is less "verbose" -- GLM really likes to comment a ton. There were a few things where I think claude would have needed a little bit less back and forth. So opus still has an edge, but it's marginal, very much unlike previous open/competitor models where benchmarks looked good but actual day to day performance was pretty bad. I'm sure fable is "better" but it's so expensive + data retention policies are such that for the moment it was generally available I couldn't use it for work. This is still notably better performance than when claude code took the industry by storm.

I'm understanding why Dario is trying to regulate open weight models away.

Not that it would make any sense.

Claude Code is an agent harness, not an LLM.

Claude is a brand (or group of LLMs), not an LLM.

Or is there a business model I’m missing?

I have more vendor lock-in with Design than I do with Code, and will switch over as soon as Claude loses the smallest technical advantage

Secondly these are "just" IDORs, arguably the easiest class of vulnerabilities.

Thirdly it compares to GPT 5.5 and Opus 4.8.

No, we don't have Mythos at home.

GPT does way worse than Opus without their harness, but better with it.

Opus 4.7 and 4.8 do way worse than 4.6. (Intentional nerfing?)

Would have been interesting to see GLM in the custom harness.

Would also be interesting to run GLM in Claude Code, which it has presumably been fine tuned on.

[0]: https://aibenchy.com/compare/anthropic-claude-opus-4-8-mediu...

Where's the cost per vulnerability for all the other models than GLM?

Also, without code this isn't very trustworthy. Could all be made up as well.

What does that mean for the frontier?

https://lifeinthesingularity.com/p/glm-52-proves-ai-comes-fo...

Thus companies who still try to have humans perform intertwined work with their AI won't see an improvement, while the ones who fin the right conditions to give their AI more free rein will see it.

Kind of like it's no use having a workhorse pull a combine harvester : at some point, when machines reach sufficient efficiency, you just give wheels to the harvester and let it run.

GPT gets there <5 minutes, GLM 5.2 without context takes ~1H.

Though the harness makes a significant difference. On Pi GLM5.2 dreams for minutes, with OpenCode it's more on the point and gets to editing quicker.

I'd be mostly fine switching to it.

I just can't find a cost effective way to do that. z.AI's coding plan is both overpriced and unreliable. ollama's is also overpriced. Paying by the token for it on openrouter etc is more expensive than just having a Codex or Claude coding plan.

If you have to pay by the token, it's clearly cheaper. It's not competitive with a coding plan though.

Beats which model in Claude? Whenever a "benchmark" doesn't put precise model numbers in their headlines I am immediately skeptical. Either they don't know the difference (bad) or they are benchmarking against weaker models (misleading, also bad).

It's like when studies say "AI is bad at X" and they used GPT-3.5 in current year.

This article only talks about detecting vulnerabilities, so it's unclear if it's a true Mythos equivalent.

So one can see businesses owning their own such cluster, next to their database infra, in the near future.

What we're they? Also, wouldn't one expect a more recently released coding agent (with a more recent knowledge cut off) to perform better because they have access to more knowledge about vulns in these OSS projects, and even possibly have knowledge of your own "prior research"?

Which I guess makes what semgrep sells obsolete. Unless they have built a pareto-optimal point in terms of capabilities and token usage maybe?

People will use the model with the harness. I know that harness may not be optimized to this model, but it's still more useful to see the numbers from an imperfect harness than from a no harness setup.

This is where we are heading and why many closed labs are terrified of this affecting their bottom line and the reason why they want them banned from being released.

Oddly, this is a strong indication of the text being hand-written rather than LLM-assisted; it's very likely that a human made a mistake in creating the table.

  > ... beating Claude Code (32%) ...

  > ... GLM 5.2 ... beat Claude Code by seven points (39% vs. 32%).


  > Rank | Configuration           | Harness         | F1
  > ...
  > 4    | Claude Code (Opus 4.6)  | Claude Code SDK | 37%

But I would like to point out that the overwhelming majority of people using LLMs aren’t programmers, don’t care about coding, and couldn’t even be bothered to “vibe code”.

So we should consider the bias of the output of these open weight models, and what that looks like, outside of the context of writing code.

After installing, do a `n8 build` to build the image, then `n8 --danger --provider opencode interactive` to launch it in a container.

Signup for GLM-5.2 here: https://z.ai

GLM may be a good model in general but it s benchmaxxed and definitely not as good as Opus 4.8.

Instead of shilling for the LLM providers.

"our IDOR benchmark", there you go.

Any good resources about this (also for setup and recommend config)?

The incentive to develop these Chinese models further is to trash the business case of most American AI labs.

additionally, reliable API, because z.ai can be finicky

also, not for Enterprise use, but I like non-US providers, I don't care if the party happens to be the one reading my information and stealing my trade secrets, if they won't respond to a US subpoena

I think the post is still informative, but very a little disingenuous and clickbaity.

What explains it?

Is TFA lying? Is the most upvoted comment here lying?