THthunderbong·Jan 5, 2025Submission
Explores regions where models fail but humans succeed
2 points · Open discussionsunildkumar
model_indistinguishability
Python2025–2025
sunildkumar / model_indistinguishability
model_indistinguishability
Explores regions where models fail but humans succeed. Based on https://arxiv.org/abs/2402.00793.
2Distinct people
3Mentions
0Explicit recommenders
6GitHub stars
What to know before exploring
What it is
Explores regions where models fail but humans succeed. Based on https://arxiv.org/abs/2402.00793.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 1:49:46 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by hour3 dated mentions
Observed mentions: 2025-01-04 21:48:48 UTC to 2025-01-05 11:24:09 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Jan 4, 21:00 | 2025-01-04 21:00:00 UTC | 2025-01-04 22:00:00 UTC | 2 | 1 | 1 |
| Jan 4, 22:00 | 2025-01-04 22:00:00 UTC | 2025-01-04 23:00:00 UTC | 0 | 0 | 0 |
| Jan 4, 23:00 | 2025-01-04 23:00:00 UTC | 2025-01-05 00:00:00 UTC | 0 | 0 | 0 |
| Jan 5, 00:00 | 2025-01-05 00:00:00 UTC | 2025-01-05 01:00:00 UTC | 0 | 0 | 0 |
| Jan 5, 01:00 | 2025-01-05 01:00:00 UTC | 2025-01-05 02:00:00 UTC | 0 | 0 | 0 |
| Jan 5, 02:00 | 2025-01-05 02:00:00 UTC | 2025-01-05 03:00:00 UTC | 0 | 0 | 0 |
| Jan 5, 03:00 | 2025-01-05 03:00:00 UTC | 2025-01-05 04:00:00 UTC | 0 | 0 | 0 |
| Jan 5, 04:00 | 2025-01-05 04:00:00 UTC | 2025-01-05 05:00:00 UTC | 0 | 0 | 0 |
| Jan 5, 05:00 | 2025-01-05 05:00:00 UTC | 2025-01-05 06:00:00 UTC | 0 | 0 | 0 |
| Jan 5, 06:00 | 2025-01-05 06:00:00 UTC | 2025-01-05 07:00:00 UTC | 0 | 0 | 0 |
| Jan 5, 07:00 | 2025-01-05 07:00:00 UTC | 2025-01-05 08:00:00 UTC | 0 | 0 | 0 |
| Jan 5, 08:00 | 2025-01-05 08:00:00 UTC | 2025-01-05 09:00:00 UTC | 0 | 0 | 0 |
| Jan 5, 09:00 | 2025-01-05 09:00:00 UTC | 2025-01-05 10:00:00 UTC | 0 | 0 | 0 |
| Jan 5, 10:00 | 2025-01-05 10:00:00 UTC | 2025-01-05 11:00:00 UTC | 0 | 0 | 0 |
| Jan 5, 11:00 | 2025-01-05 11:00:00 UTC | 2025-01-05 12:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
3 sourcesFinding inputs where deep learning models fail
3 points · Open discussionHi there! Last month at NeurIPS (an ML conference), I read an interesting paper "Human Expertise in Algorithmic Prediction" that describes a framework for determining where ML models are outperformed by human experts. I found the authors' work to be very interesting. Below, I explore their framework further and extend it to multiclass classification. My results are pretty surprising, showing that a group of modern model architectures have trouble with dogs and cats in CIFAR-10.
GitHub Link: https://github.com/sunildkumar/model_indistinguishability
Paper Link: https://arxiv.org/abs/2402.00793
In Finding inputs where deep learning models fail