I'm working on exactly this! I'm building a small model that classifies the correct DOM node containing an HTML's article content/title/date/author (given a raw html with a lot of noise/chrome). A fun learning exercise :)
30KB model, 40-50ms inference. Pretty happy with the results so far!
I can see an entire industry of tiny models like this, now that we have AI to help us do the grunt setup work (validation/training data creation, data cleaning, etc). Or just use a general classifier like Jev/Kev ha
> I find the post cursor groks are phenomenal at frontend web development, though Claude is much better at backend ruby.
Wonder if we'd benefit from a much more specialized + task-specific benchmarks to paint a clearer picture like this. A benchmark solely for frontend, ruby, hardware, etc.
If you found this interesting, I highly recommend reading "The Righteous Mind" by Jonathan Haidt. It's deeply impacted how I think of morality and politics from a societal and psychological point of view.
Some ideas in the book:
- Humans are tribal, validation-seeking animals. We make emotional snap judgments first and gather reasons to support those snap judgments second.
- The reason the political right is so cohesive (vs the left) is because they have a very consistent and shared understanding and definitions of what Haidt calls the 5 "moral taste receptors" - care, fairness, loyalty, authority, sanctity. Whereas the left trades off that cohesive understanding with diversity.
I've really enjoyed Haidt's book, though its really a couple of different books in one. I need to read his other work.
To your point about left and right, an interesting point I heard recently is that the left is coalition-driven whereas the right is consensus-driven (at least in US politics). Mapping this back to Haidt, one of his findings is that the left tends to greatly emphasize one or two of the "moral taste receptors", with the right having a roughly equal emphasis between them. It isn't clear to me how these two points might explain each other, but I do wonder if there isn't some self-reinforcement there. If there is, I wonder how/if that might explain political systems more widely.
>>The reason the political right is so cohesive (vs the left)
Citation excruciatingly needed. This feels like recency bias imo. The Right (I'm assuming we're going US here?) is a coalition of people all walks just as much as the left. I mean, right now large chunks Trump voters are rioting over the Epstein non-release and all the people who were in it for the tax breaks are trying to convince them to stop.
Hi Peter! Thank you for doing this. Are you seeing any issues/concerns with Green Card holders traveling internationally and returning to the US in the past few months?
Only that even with green card holders, we have seen instances where CBP is asking to see electronic devices and reviewing their social media accounts. But we haven't had a green card holding client detained or denied admission.
lol. in LA everyone's instagram just shows ICE getting beaten and the epstein files posts that follow these. I wonder how fun it must be to travel nowadays.
> Strong engineers, however, can break out the two problems and solve them at the same time.
Disagree so much with this. A "good" engineer breaks a problem down, solves them one by one, and avoids mentally juggling multiple things at once if possible.
30KB model, 40-50ms inference. Pretty happy with the results so far!
I can see an entire industry of tiny models like this, now that we have AI to help us do the grunt setup work (validation/training data creation, data cleaning, etc). Or just use a general classifier like Jev/Kev ha
reply