Why does OpenClaw have 800,000+ lines of code?? Isn't it just a connector for LLM APIs and other tools?

For comparison, the C++ and rust code in the ladybird browser is about 573,000 lines of code.

They are probably counting dependencies. Also, it's vibe coded, what do you expect!

I used to think that LLMs would replace humans but now I'm confident that I'll have a job in the future cleaning up slop. Lucky us.

I did a cloc check on it and it does seem to have 800k lines of typescript. So unless they are vendoring dependencies it's actually as insane as it sounds.

Christ their repo is an absolute nightmare. There's new issues and PRs being posted practically every minute, and I assume 99% of them are from agents given the target demographic. Just full-auto vibeslop from all barrels 24/7.

Even if we count the repos whole lifetime, including when it wasn't so active, the averages are still absurd.

96 days / (4,239+9,170) issues = one issue every 10 minutes

96 days / (5,082+10,221) pull requests = one PR every 9 minutes

5000+ open PRs is pretty insane, that's the highest I've seen. How do you even keep track of this? We'll really need trust management systems like vouch (https://github.com/mitchellh/vouch/tree/main) for open source projects in the future to help with reducing noise.

At least nobody can accuse them of not dogfooding enough.

I assume it is mostly or entirely written by AI, so that tracks.

See also yeggae's beads. Last I checked, it is a 275k line todo tracker.

> Why does OpenClaw have 800,000+ lines of code??

Because

I

write

like

this

-- signed

AI

It's just hallucinating training data, the model is very small so it cannot be useful at all

The name of the article is misleading, probably some clickbait since it's talking about ASI

Still, it's a good reminder that AGI is not a 'superintelligent' entity but just a _general_ intelligence

Yes, in "runtime optimization" the model is just a computation graph so we can use a lot of well known tricks from compilation like dead code elimination and co..

We are getting closer!

What other optimizations are there that can be used than what explicitly falls into the 4 categories that the top commenter here listed out?

For inference assorted categories may include vectorization, register allocation, scheduling, lock elision, better algos, changing complexity, better data structures, profile guided specialization, layout/alignment changes, compression, quantization/mixed precision, fused kernels (goes beyond inlining), low rank adapters, sparsity, speculative decoding, parallel/multi token decoding, better sampling, prefill/decode separation, analog computation (why not) etc etc.

There is more to it, mentioned 4 categories are not the only ones, they are not even broad categories.

If somebody likes broad categories here is good one: "1s and 0s" and you can compute anything you want, there you go – single category for everything. Is it meaningful? Not really.

Thanks!

You should know that there is already a solution for this, SafeTensors [0].

But it may be a nice tool for those who download "unsafe" models

[0]: https://huggingface.co/docs/safetensors/index

It seems like this project has decided that .safetensors might not be so safe after all, since it's scanning them too, according to https://drive.google.com/drive/folders/1G-Bq063zk8szx9fAQ3NN... at least.

Safetensors is the goal, but legacy models are still there. A massive portion of the ecosystem (especially older fine-tunes and specialized architectures) is still stuck on Pickle/PyTorch .bin. Until 100% of models migrate, we need tooling to audit the "unsafe" ones.

It's just Anthropic being Anthropic, nothing new