Show HN: I have trained 15 blood glucose forecasting models on my own data
0xdeadf1sh
15 points
3 comments
November 10, 2026
Related Discussions
Found 5 related stories in 123.3ms across 12,324 title embeddings via pgvector HNSW
- Show HN: T0: We trained a 256M SOTA open-weights time-series forecasting model LTMeyer · 12 pts · October 14, 2026 · 61% similar
- Show HN: I trained a 125M model to autocomplete piano on-device simedw · 539 pts · August 20, 2026 · 54% similar
- Show HN: How Stale Is Your AI? Release age and training cutoff for 20 models joozio · 71 pts · September 16, 2026 · 53% similar
- Show HN: I implemented a neural network in SQL alxmrs · 76 pts · July 13, 2026 · 52% similar
- Show HN: Free Inference Engineer and Model Training Roadmap jesse_portal · 16 pts · August 24, 2026 · 51% similar
Discussion Highlights (3 comments)
nuthje
89% TIR, well done! Cool to see the research, I’m surprised there aren’t more in-depth n=1 studies out there from statistics/data-savvy diabetics. I built a small dashboard exactly collating carb, insulin, sleep, and movement data and trying to coax out useful correlations to help manage. Some interesting insights, but clearly I should eat less and move more. Keep up the good work, and thanks for sharing!
Bigchrome
I achieved 100% TIR with my model. I'm not T1D, but same same. JK, as the spouse of someone with T1D I really appreciate seeing this!
zenpositive
Very cool very nice work!