Get the latest tech news
I used o3 to profile myself from my saved Pocket links
Welp, Pocket shuts down tomorrow despite our pleas for it to stay. While migrating1 all of my saved articles, I noticed that I’ve got almost 900 saved articles spanning nearly 7 years. That’s a goldmine of stuff-I-like data! Some quick analysis using xsv2: 𝄢 unzip pocket.zip && xsv headers part_000000.csv 1 title 2 url 3 time_added 4 tags 5 status 𝄢 xsv sample 1 part_000000.csv | xsv flatten title The Uncertain Future of American Libraries url https://mek.
Recalling Simon Willison’s recent geoguessing challenge for o3, I considered, “What might o3 be able to tell me about myself, simply based on a list of URLs I’ve chosen to save?” I opened a temporary chat with o3 (doesn’t use ChatGPT’s memory feature) and prompted: at least one toddler)Twin-mom sleep articles, Catholic “family table”, homeschooling & microschools piecesDimensionInferenceRationale Politics Fiscally conservative / civil-libertarian with traditionalist social leaningsBogleheads & MMM frugality + Catholic/First Things pieces, EFF privacy, skepticism of Big Tech censorship Risk toleranceCareer: high (security research, side projects) Financial: moderate (indexing, 4 % rule, self-sufficiency)Mix of daring technical reading and ultra-conservative portfolio design Learning style Self-directed, text-heavy, long-form + auditoryUses Pocket/RSS, collects PDFs, long podcasts & conference talks at 1× Information diet 60 % deep-tech, 20 % personal finance/FIRE, 10 % parenting/homemaking, 10 % faith & cultureCounts of saved links across themes Major life arc Phase shift: from pure IC hacker → technical leadership & family-centric life, aiming for FISaves on management paths, burnout, early-retirement reflections Seasonal spikes Late Dec–Jan: career-planning & goal-setting; May–Aug: homeschooling, beach/sea-level, property; Sep–Oct: security-conference binge (DEF CON, Black Hat)Timestamp clusters in list Faith: Regular saves from Catholic & conservative Christian sites suggest active practice. We already know that advertising companies profile us based on expressed interests, but up until recently it felt like only Google or Facebook had access to analysis capabilities strong enough to draw meaningful conclusions from disparate data points.
Or read this on Hacker News