Firefox

And I still can't convince it to stop caching the images because it does not follows the RFC.

Luckily, it seems to be disabled by default. At the moment.

I wonder if this can be removed at compile time, like Pocket.

Sigh. I'm glad to have switched to LibreWolf.

Wasn't this there for a while, or just me.

Unpopular opinion, I think they're doing it right as well as it can be at least. It's completely optional and doesn't seem to be intrusive.

Wow, great job Firefox. Thanks.

If I wanted unreliable bullshit like AI, I'd use Chrome.

Didn't want it in Opera, don't want it in Firefox. I mean they can keep trying and I'll just keep on ignoring this shit :/

I don't understand the hate. It's just a sidebar for the supported LLMs. Maybe I'm misunderstanding?

Yes, I would prefer Mozilla focus on the browser, but to me, this seems like it was done in an afternoon.

This happened ages ago, didn't it? Am I missing something new?

I will say, the Le Chat provider is pretty decent. You really can use it more natural language. "Rewrite it with a better rhyme scheme" "remove the last line" and it just got it.

Why no local option though? Why no anonmysing option?

Edit: There is a right click option which does make this officially actually useful for me now (summarize this!).

Other models do have RAG options and Mist real supports making agents with specified documentation too to at least fine tune too (not as good as full grounding though IMHO)

If they do it in a privacy-preseeving way, this could help them get back market share which will generally benefit an open internet.

Thing is, for your average user with no GPU and whp never thinks about RAM, running a local LLM is intimidating. But it shouldn't be. Any system with an integrated GPU, and the more RAM the better, can run simple models locally.

The not so dirty secret is that ChatGPT 3 vs 4 isn't that big a difference, and neither are leaps and bounds ahead of the publically available models for about 99% of tasks. For that 1% people will ooh and aah over it, but 99% of use cases are only seeing marginal gains on 4o.

And the simplified models that run "only" 95% as well? They can use 90% fewer resources give pretty much identical answers outside of hyperspecific use cases.

Running a a "smol" model as some are called, gets you all the bang for none of the buck, and your data stays on your system and never leaves.

I've been yelling from the rooftops to some stupid corporate types that once the model is trained, it's trained. Unless you are training models yourself, there is no need for the massive AI clusters, just for the model. Run it local on your hardware at a fraction of the cost.

I mean, if you're going to do it, where's the Ollama love?

Thanks for nothing, Mozilla.

Now add support for GPT4All and everyone is happy again.

That was there before 133, don’t remember the exact release that added it.