A good teacher meets the student where they are

No. 234 of 245 · Perplexity AI · published 23 Oct 2026, 09:56 UTC · 10 min read

AI & machine learning
Paper

2 judges. Scored by two of the three judges. The third reads only the day’s strongest candidates. How far stories are checked

JOLT (Joint On-policy Learning and Teaching) proposes training a single model as both a privileged-information teacher and an unprivileged student, so that the teacher's guidance is shaped to be useful to the student rather than merely correct.

Read the original at perplexity.ai. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Score

0.55total under rubric v2.0

Significance0.51
Reader interest0.59
Audience breadth0.48
Practical relevance0.47
Substantiated0.75
Technical depth0.91
New information0.85
Counts against: Promotional0.12
Counts against: Overclaim0.29

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

Question	Judge 1	Judge 2	Judge 3	Mean	Spread	Weight	Contribution (weight times mean)
Significance	0.62	0.40	—	0.51	0.22	+0.25	+0.127
Reader interest	0.63	0.55	—	0.59	0.08	+0.20	+0.118
Audience breadth	0.57	0.40	—	0.48	0.17	+0.10	+0.049
Practical relevance	0.55	0.40	—	0.47	0.15	+0.15	+0.071
Substantiated	0.90	0.60	—	0.75	0.30	+0.10	+0.075
Technical depth	0.97	0.85	—	0.91	0.12	+0.10	+0.091
New information	0.90	0.80	—	0.85	0.10	+0.10	+0.085
Promotional	0.09	0.15	—	0.12	0.06	−0.15	−0.018
Overclaim	0.24	0.35	—	0.29	0.11	−0.15	−0.044
Sum of contributions							+0.554
Claim-check penalty							0.000
Total, as published							0.553

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested. Judge 3 did not score this story; its mean uses the other two.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 3 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 24 Oct 2026, 08:54 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition and listed in its JSON. This one was scored under rubric v2.0; How ranking works describes the current rubric, v2.2.