stochastictrebuchet

ML engineer here. My intuition says you won’t get better accuracy than with sentence template matching, provided your matching rules are free of contradictions. Of course, the downside is you need to remember (and teach others) the precise phrasing to trigger a certain intent. Refining your matching rules is probably a good task for a coding agent.

Back in the pre-LLM days, we used simpler statistical models for intent classification. These were way smaller and could easily run on CPU. Check out random forests or SVMs that take bags of words as input. You need enough examples though to train them on.

With an LLM you can reframe the problem as getting the model to generate the right ‘tool’ call. Most intents are a form of relation extraction: there’s an ‘action’ (verb) and one or more participants (subject, object, etc.). You could imagine a single tool definition (call it ‘SpeakerIntent’) that outputs the intent type (from an enum) as well as the arguments involved. Then you can link that to the final intent with some post-processing. There’s a 100M version of gemma3 that’s apparently not bad at tool calling.

Locally sourced and by free-range developers

Comic Code gang represent

Any time I read the Kitty docs I’m just in awe of everything its maker, Kovid Goyal, has built for it. Like, not just individual features but entire protocols, which other terminals then adopt.

I just wish remote session persistence was more of a priority. Goyal dislikes tmux (to put it mildly) but doesn’t suggest an alternative to those who do their work on remote servers. If I’m already organizing my work in tmux over ssh, I might as well do the same locally as well – which unfortunately means missing out on some of Kitty’s best parts.

From what I’ve read the former president actually got quite a lot done. It just didn’t get talked about as much, at least in international news.

Man, those were good days…

To the extent that the billboard never existed while the image implies it did – sure.

I love the term ‘slop’. It’s one of my favorite new words along with ‘nontent’.

But this, to me, isn’t that. I think of slop as ‘unrequested, unconvincing, lazy, and lifeless’. In short, ineffective and unwelcome.

I feel like this meme gets the message across. It’s not great, but it’s not terrible. The AI tells are subtle enough: the multi lane pileup in the background and some poor small size text rendering.

Not sure why I felt the need to write this. Guess I’m of the opinion that just because something is AI-generated doesn’t mean it should be discounted immediately, unless it really feels like zero effort went into it. Have a nice day!

Task failed successfully

‘Small businesses’