barapa

no profile record

barapa

3 か月前議論

I find it useful to have goons on payroll that make these kinds of problems go away

barapa

4 か月前議論

I promote people for simplicity

barapa

5 か月前議論

how is this a company?

barapa

7 か月前議論

I don't find this all that compelling. Different technologies can have different effects. And why would future effects be influenced by the accuracy of random people's predictions of other events in the past?

barapa

7 か月前議論

I think mine confabulated criticism of a point of view as espousing that point of view.

barapa

8 か月前議論

don't loving these

barapa

8 か月前議論

We have done a lot of work solving this exact challenge at legaide.ai. I was both sad and relieved when gemini 3 didn't deprecate our startup.

barapa

8 か月前議論

I don't really understand this. You can and should tell the llm the source of the search results.

barapa

9 か月前議論

We often will repeat calls to try again. Or sometimes we make the same call multiple times to get multiple answers and then score or merge them.

Is this used only in cases where you assume the answer from your first call is correct?

barapa

9 か月前議論

Smart invisible regex makes it fast and prevents it from crashing? What does that mean?

barapa

9 か月前議論

I implemented copy to clipboard in datastar in maybe 1 minutes with an AI agent. What exactly are you providing to the world for free?

barapa

9 か月前議論

Chill dog

barapa

10 か月前議論

Yes, things change. In fact, change is basically the only thing you can confidently predict.

barapa

10 か月前議論

If things disappear, that is ok. Everything is fleeting.

barapa

10 か月前議論

[flagged]

barapa

10 か月前議論

They are training on your queries. So they may have some exposure to them going forward.

barapa

11 か月前議論

I really don't like Dia. Hijacking the search bar to use their own AI model, which is just slower than google's AI mode is such a bad experience. I am happy for chrome to have built-in AI tools when needed.

コメント