It's a huge step though.

The pyproject.toml can even handles build env for you, so you no longer need a setup.sh that installs 10 tool in specific order with specific flag to produce working environment. A single uv sync, and the job is done.

Plus the result is reproducible, so if this time uv sync work, then it also work next time.

Highly recommend if you are still on pip.

Note: Take a example that I used to install unsloth with rocm setup that based on unreleased git version dependencies and graphic card specific build flag, all of them can be handled with one command 'uv sync'. This will require a big pile of shell script if doing another way. https://github.com/unslothai/unsloth/issues/4280#issuecommen...

and windows mostly use \? and also \h,

java user single - for long argument because it don't have short one.

I doubt it is ever close to reusable.

And even allowed position of parameters (or even meaning of arguments in case of ffmpeg) are program dependent.

Some allow anywhere as long as it is started with a dash, some only allow before first input

And it's also affected by how model is trained. Gemini specifically like to read large amount of text data directly and explodes the context. But claude try to use tool for partial search or write a script to sample from a very large file. Gemini always fills the context way faster then claude when doing the same job.

But I guess in case of a bad designed mcp, there is no much model can do because the results are injected into context directly though (unless the runtime decided to redirect it to somewhere else)

You can probably let llm guess the help flag and try to parse help message. But the success rate is totally depends on model you are using.

However that don't happen unless firefox just stop developing though. New code comes with new bug, and there must be some people or some tool to find it out.

This sounds like your context is too big and getting cut off.

They also finally fix all ai related stuff building on windows, so you are no longer limited to linux for these.

I made a mixed extraction, cleaning, translation, formatting task on job that have average 6000 token input. And so far, only 30b a3b is smart enough not miss job detail (most of time)

I later refactor the task to multi pass using smaller model though. Make job simpler is still a better strategy to get clean output if you can change the pipeline.

Recently, I am trying to make llm to output specific format.

It turns out no matter how you wrote propmt and perform validate. It will never be as effective as just limit the output with proper bnf (via llama cpp grammar file).

And there isn't really a way to confirm if it is configured in a secure way.

You either trust the developer or not.

Besides that, almost all online game except for a few provide item though the in game store. I don't think they even need to pay for a cent to valve unless they want to use steam checkout service.

I wonder who ever used Steam would even buy this argument. It looks totally non-sense to me.

Firefox and safari are generally very conservative about new api that can enable new type of exploits.

At least firefox and safari does implement origin private file system. So, while you can't edit file on user disk directly. You can import the whole project into browser. Finish the edit and export it.

This is so real. Sometimes when you get a unreasonably big feature request. It always turns to be somebody don't know how to express their request correctly. And the management overexerted it.

Knowing things is bad only requires knowledge of the product itself. But fixing it requires understanding of the whole infrastructure and members around the project.

An outsider can't do it. And the insider don't necessarily think the project is bad from his perspective. You would have to argue with him to convince him the project is bad. Which really don't bring any value to the outsider themselves. And it can even be harmful.