I wrote an ai agent that do chrome testing, yes, chrome MCP do work https://github.com/netdur/hugind/tree/main/agent/chrome_test...

Did it complain about copyright issues?

Gemini 3 long context is not good as Gemini 2.5

I'm 100% sure that all providers are playing with the quantization, kv cache and other parameters of the models to be able to serve the demand. One of the biggest advantage of running a local model is that you get predictable behavior.

Now you know why Superbowl ads cost millions and bloggers are just bloggers

I have tried to solve the agent running wild, and I found two solutions, the first is to mount the workspace folder using WASM to scope any potential damage, the second is running rquickjs with all APIs and module imports disabled, requiring the agent to call a host function that checks permissions before accessing any files

--- [0] https://github.com/netdur/hugind

While there is nothing wrong about Saudi money, they are spreading FUD about open weights and wants to regulate and control how the LLM is used

Regulation is not always bad. What’s the FUD you refer to?

i would love if you took the time to instruct claude to re-implement inference in c/c++, and put an mit license on it, it would be huge, but only if it actually works

FWIW stable-diffusion.cpp[0] (which implements a lot more than just stable diffusion, despite the name) is already a MIT licensed C++ library.

[0] https://github.com/leejet/stable-diffusion.cpp/

calculators doing a perfect job did not end accountants' jobs, it made it faster.

I don’t think that’s as good of an example as you think it is.

“Computer” used to be a job title. It was entirely replaced by … drumroll … electronic computers, i.e. calculators.

Technology doesn’t usually eliminate the need for a job output in general but it can sometimes shift the skills needed wildly.

Not necessarily faster, but more easy for sure. There's plenty of stories of proficient abacus using accountants being faster than those using calculators. Those days are gone now though because a calculator is just so much easier to pick up.

Your sort of paying them to understand the tax code that changes year to year tho

they have been doomed for a while, it is just a matter of time, but honestly i like them better than the claude provider, if they can make openai profitable, that would be good for all of us, we don't want a world where gemini is the only winner or the chinese take over

Anthropic thinks highly of its "moat", yet it is spreading FUD to kill open weights