I've had the domain for a while as a someday-maybe and figured I had to jump onto the bandwagon! Partly as a challenge to stop navel gazing and ship something. Started yesterday morning, had a chat with ChatGPT on the bus, cleaned up last night and this morning.
I wanted to maximise the Cloudflare static caching and not fiddle too much with security, so it's 400-ish data chunks and each repo should have a stable hash. I only use everything down to 10 mentions since the long tail is long. Might revisit that later, but this gets me published.
Using Google BigQuery and GCP a lot, Jev for classification, Codex as an agent with GPT-6.1 Sol High.
Comments URL: https://news.ycombinator.com/item?id=50342272
Points: 2
# Comments: 0
