Trendoday

Show HN: I have trained a model to predict my blood sugar

1 comments

  • Points5
  • Comments2
–Rank now
#15Peak rank
1Days on list
86Score · 7d
Nov 14, 2026First seen
Rank · 7 days

On Hacker News

I have trained a custom 31,253 parameter encoder-only transformer on a pregenerated synthetic CGM dataset and fitted it to my own personal data using LoRA. It is competitive among other published models. I used 115 days of CGM data, of which 80 was used for training the adapter and 35 for testing. The model began with a pretraining stage where it consumed ~19,200 CGM-years worth of synthetic data, consisting of 1 million simulated type 1 diabetics at 7 days each. The simulator is designed to…

Points
5
Comments
2
Submitted by
0xdeadf1sh
Posted
Nov 13, 2026
Site
github.com

Story details from Hacker News ↗ · linked article on github.com.

Trending history

Show HN: I have trained a model to predict my blood sugar was first seen on Hacker News · Show HN on Nov 14, 2026. Since then it has appeared in 25 checks on 1 different day. Its best position was #15 of 30, reached on Nov 14, 18:22 UTC. It dropped off the list after Nov 14, 20:52 UTC.

Rank history

Position on Hacker News · Show HN at every check (lower is better).

#1#11#20#30 08:5211:5214:5217:5220:52 Nov 14, 08:52 UTC · #25Nov 14, 09:22 UTC · #25Nov 14, 09:52 UTC · #25Nov 14, 10:22 UTC · #27Nov 14, 10:52 UTC · #28Nov 14, 11:22 UTC · #27Nov 14, 11:52 UTC · #27Nov 14, 12:22 UTC · #26Nov 14, 12:52 UTC · #25Nov 14, 13:22 UTC · #25Nov 14, 13:52 UTC · #23Nov 14, 14:22 UTC · #20Nov 14, 14:52 UTC · #23Nov 14, 15:22 UTC · #19Nov 14, 15:52 UTC · #18Nov 14, 16:22 UTC · #18Nov 14, 16:52 UTC · #19Nov 14, 17:22 UTC · #21Nov 14, 17:52 UTC · #21Nov 14, 18:22 UTC · #15Nov 14, 18:52 UTC · #15Nov 14, 19:22 UTC · #16Nov 14, 19:52 UTC · #16Nov 14, 20:22 UTC · #17Nov 14, 20:52 UTC · #17

Last 14 days

Best rank per day (UTC).

Nov 3today

Metric history

Platform metric as reported by Hacker News.

0235 08:5211:5214:5217:5220:52 Nov 14, 08:52 UTC · 3Nov 14, 09:22 UTC · 3Nov 14, 09:52 UTC · 3Nov 14, 10:22 UTC · 3Nov 14, 10:52 UTC · 3Nov 14, 11:22 UTC · 3Nov 14, 11:52 UTC · 3Nov 14, 12:22 UTC · 3Nov 14, 12:52 UTC · 3Nov 14, 13:22 UTC · 3Nov 14, 13:52 UTC · 3Nov 14, 14:22 UTC · 4Nov 14, 14:52 UTC · 4Nov 14, 15:22 UTC · 4Nov 14, 15:52 UTC · 4Nov 14, 16:22 UTC · 4Nov 14, 16:52 UTC · 4Nov 14, 17:22 UTC · 4Nov 14, 17:52 UTC · 4Nov 14, 18:22 UTC · 5Nov 14, 18:52 UTC · 5Nov 14, 19:22 UTC · 5Nov 14, 19:52 UTC · 5Nov 14, 20:22 UTC · 5Nov 14, 20:52 UTC · 5

From the discussion

A few top-level comments from Hacker News, shortened. Read the full thread on Hacker News.

I wrote a website that helped my wife's grandfather manage his diabetes. It was essentially captured that moment in time his blood sugar, blood pressure, and weight. This was 10 years ago, and his doctor loved it because he could generate a report and bring it to his visits. What you're doing here is far beyond what…

Questions

Is Show HN: I have trained a model to predict my blood sugar trending on Show HN right now?

Not at the moment. It was last on the list on Nov 14, 20:52 UTC, after 1 day of trending.

What is the highest rank Show HN: I have trained a model to predict my blood sugar reached?

#15 on Hacker News · Show HN, on Nov 14, 18:22 UTC. Trendoday checks this list every 30 minutes.

How long has Show HN: I have trained a model to predict my blood sugar been trending?

It was first seen on Nov 14, 2026 and has been on the list on 1 day (25 checks) since.

How much discussion did it get on Hacker News?

5 points and 2 comments; submitted by 0xdeadf1sh on Nov 13, 2026.