If you think training a sparse autoencoder to extract concept vectors that are usable as steering injections into a modern LLM is pretty easy, you should probably go work for Anthropic's mech interp team ;)
It's a very complex joint (which is why it's never been done before that I could find --- hopefully will be patentable), and the tool definition probably wasn't optimal, nor the CAM tool being used appropriate to the task, hence my working on developing the toolpaths more directly.
"Precision, for LEGO, isn't an engineering choice, it's a brand promise." - The classic "It's not just x, it's y", just minus the "just".
"One philosophy optimizes for cost, the other for perfection." - Again we see the x/y structure; AI writing often features these forms, eg comparisons (x vs y), conversions (x into y), negated emphasis (not x, but y), etc.
"When you have multiple parts in an assembly, use statistical analysis for tolerance stack-up rather than worst-case math. Traceability matters. Track your defects so feedback turns precision into reliability." - More x/y followed by a short stinger ("Z matters"), and the closing sentence again follows the "x/y" pattern.
For funsies I tossed the whole thing into a purported AI detector and it said 90+% confidence of AI. I don't trust those types of things very much and suspect they have high false positive rates, but I have read that AI writing generally has measurably lower entropy, so maybe it's plausible, and in this case it aligns with my existing beliefs, so it obviously must be true.
Fascinating interview - hearing two women of Chinese extraction working in the West candidly discuss their cultural origins and its effect of their mental state (dynamism vs scorn for weakness, the anxiety of stagnation), the specifics of Chinese worker culture (shamate, factory towns), and the inside view on "Belt & Road" in practice (empty sloganeering, lack of investment experience, etc) all really expanded my view of China. It's easy to get lost in the Western, pseudo-propagandized perception of China, and hearing the views of people who've truly seen both sides is a rare and valuable experience. Worth reading in its entirety, and I intend to watch the film now, too.
Indeed, sci fi has always been a way for KSR to explore and animate his politics. But he's so skilled a writer that the spectacle and incredible technical detail of the sci fi wrappings can obscure subtlety of the political philosophy (as it should be, imo).
Agree, except I thought his political views were rather more obvious, to the point that it's a little annoying (IMHO of course). I'd describe it more as hard-left than anarchism, too.
Inside the repo as metadata that can be consumed by a provider, like GHA config in .github/. Standardized, at least as an extension like git lfs so it's provider independent. Could work! I've long thought effective reputational models are a major missing piece of internet infrastructure, this could be the beginning of their existence given the new asymmetric threat of LLM output, combined with mitchellh's productivity and recognition.
reply