Hi. I'm a computer programmer and person educator. These are some of my thoughts, published as an error detection and correction exercise. Please fee...
A comment I've seen a few times from the LLM-reluctant software people goes like this: If the models are getting easier to use with each generation, then there's no real penalty for being a late adopter. The premise is true: the tools are getting easier to use - for more tasks and by a wider user base. But the conclusion is false. If the tools get easier to use for many tasks, the market value for…
For abundance liberals annoyed by leftist preconceptions about economics (see, for example, the argument on a recent John Stewart + Richard Thaler interview), I have a proposal: Reset assumptions with a little rebrand: Markets ? Consumptive. Competitive. Zero sum. Morkets ? Generative. Constructive. Positive sum. Gimme some more. PS - open question about morkets vs morekets spelling.
JOY / WOE Jan 2026 STATUS UPDATE Joys of the Craft Creating things of one’s own design - much more joy. Making something useful to others - vague mixed bag. Building and watching complex systems work - bit of a mixed bag because some of the more physical putting together aspects are now gone, but overall more joy now. Continual learning from nonrepeating problems - more joy, maybe much more.…
When claude-code or gemini-cli chums along, they rotate some verb phrases as feedback to the user. Sometimes they are on topic, but often they are a bit silly or even self-deprecating. vibing hullabalooing putzing Cute. But where the hell have hallucinating , confabulating , subtly missing the point , and blithely eating your token allotment been? Come on. You're crossing the chasm now - it's time…
Simon Willison asks : What's the latest research on how much baked-in knowledge an LLM needs in order to be useful? If I want a specialist coding model can I trim the size of that model down by stripping out detailed knowledge of human history, geography etc? Can we even do that? Andrej Karpathy describes work toward such a system The race for LLM "cognitive core" - a few billion param model that…
To notify is to provide information, to reduce uncertainty, to not if the perspective of the notified. Shortened from prior notiffy , in turn a compound of the phrase not iffy .
And what do you do here? I refresh. Why do you refresh? To forget. To forget what? To forget that I am bored. What are you bored of? Refreshing!
Here's a recent prompt I threw at Claude Sonnet 4: to `.me.bashrc`, add a alias or fcn `dictate` that: runs - sudo systemctl restart dictation.service - systemctl --user restart dication_tray.service if either restart fails, (does restart fail if something is not already running?), try again with a plain `start` (ignore this if not necessary) suggestion alternatives if bundling these doesn't work…
A Lesson , attended to, can help prevent you from becoming a moron. Still unknown: on what?
I've engaged in more software planning and development discourse with Claude models than any individual human. An aggregate history of my Anthropic account is probably higher signal of my software acumen and taste than my github account, and certainly higher than my resume or my LinkedIn account. So - when ClaunkedIn? (dibs on royalties for the name) Absolutely nightmarish surveillance issues…