Edition of Wednesday 18 November 2026

Last year we built megakernels. This year we deleted them: The road to TKCC

Comments on “Last year we built megakernels. This year we deleted them: The road to TKCC”

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

Together AI's engineering team reports that after building "megakernels" that ran an entire model forward pass in one fused GPU kernel, they found most of the gains could be recovered with simpler tools: CUDA Graphs and PDL on top of default Torch Inductor kernels recovered 98% of megakernel performance, and…

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

Why it ranked

No. 64 of 142 with a score of 0.64. The panel rated it highest on technical depth (0.92) and new information (0.92), lowest on audience breadth (0.61). Placed No. 64, No. 51 by score alone: the 24th AI & machine learning story of the day (−0.080), and close to “Tang, a compiler that derives GPU kernels and bounds how fast they can run”, No. 6 on Thursday 12 November 2026 (−0.004). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Detailed, technically deep engineering write-up on GPU inference optimization (megakernels vs CUDA Graphs/PDL), with measurements, but self-promotional vendor framing and mostly internal lessons.
AI judgeJudge 3gpt-5.6-luna
Detailed engineering account of AI inference optimization, with reproducible measurements, GPU/compiler specifics, and practical lessons about megakernels, CUDA Graphs, PDL, benchmarking, and agent-driven optimization. Some promotional framing, but substantial evidence supports the conclusions.

Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.

Score

0.64total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.64
  • Reader interest0.78
  • Audience breadth0.61
  • Practical relevance0.71
  • Substantiated0.76
  • Technical depth0.92
  • New information0.92
  • Counts against: Promotional0.25
  • Counts against: Overclaim0.35

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

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.650.450.820.640.37+0.24+0.154
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.720.700.930.780.23+0.26+0.204
Audience breadthHow many people who build technology does it concern?0.610.500.720.610.22+0.13+0.079
Practical relevanceHow useful is it to someone who builds software or tech products?0.670.600.860.710.26+0.22+0.156
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.830.600.860.760.26+0.05+0.038
Technical depthHow technically substantive is it?0.990.800.980.920.19+0.05+0.046
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.910.851.000.920.15+0.05+0.046
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.110.350.280.250.24−0.19−0.047
OverclaimDo the headline or conclusions claim more than the body supports?0.490.350.200.350.29−0.11−0.038
Sum of contributions+0.638
Claim-check penalty0.000
Total, as published0.638

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.

Ranked #64 on Rubric, 18 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-18/64/"><img src="https://rubric.hrih.si/badge/2026-11-18/64.svg" alt="Ranked #64 on Rubric, 18 Nov 2026" width="245" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 2 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 18 Nov 2026, 05:47 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. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “Last year we built megakernels. This year we deleted them: The road to TKCC”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.