one-million-checkboxes (src) ——

i’ve always been so impressed by the work that nolen creates. i think there’s a mix of both whimsy / fun and dedication / neuroticism which i am personally such a fan of. his voice is so unique (a beautiful blend of earnest and humorous) and also optimistic. i also really appreciated his vulnerability in previous posts on addiction (something i’ve personally struggled with), that genuinely bring me to tears. and as silly as this game is, the level of love put into this game also brings me to tears.

[... 387 more words to read 📓 ]
guessing games to remember words (src) ——

something i’ve been struggling with personally is how much to offload to llms. on one hand — the technology is fascinating, powerful, and enables me to learn and do more than before. on the other hand — it dulls my technical skills and robs me of learning opportunities.

[... 447 more words to read 📓 ]
twelve factor agents (src) ——

this is an interesting piece by Dex Horthy of HumanLoop (an ai startup working in the LLMOps space). it mimics herokus “12 factors apps” (of which i was honestly unaware of, my inexperience is showing 🙈). i've listed some takeaways below!

[... 785 more words to read 📓 ]
ask hank anything: jacob collier (src) ——

recently, hank green — one of my favorite creators and someone i’ve been watching since i was 10 years old — has been hosting a series called “ask hank anything”. in it, he brings guests to ask their questions ahead of time, so he can give a well researched answer — the idea being that a persons questions can often tell you a lot about them

[... 1168 more words to read 📓 ]
decompiling executables with llms (src) ——

an interesting blogpost by Geoffrey Huntley showing how llms can be used to "decompile" applications with bundled / minified code (and in a following post) they show it can also be done for assembly. i think this is especially interesting (and concerning for the creators) of electron applications, as there's relatively accessible source code in languages and frameworks that llms are actively being trained on, though i imagine there will be a day that most compiled apps can be undone.

[... 358 more words to read 📓 ]
simonwillisons approach to running a linkblog (src) ——

simonwillison's description of how to run a link blog, with little bits of why as well. simonwillison's output has been prolific over the past few years. he is a voice i trust in llms — a field which is hard for me to find trusted voices in — and part of that trust comes frm his prolific linkblog. he introduced me to the term, sharing snippets of summaries, contexts, and opinions on happenings throughout the internet and technology,

[... 406 more words to read 📓 ]
test page (src) ——

Hey there 👋🏾! You're visiting a bit early, so you get to see my test page. Hope you enjoy reading some latin :).

[... 361 more words to read 📓 ]
🔎 2025-03-01