Deterministic AI: Why LLMs Aren't, and How to Build Products That Are Anyway
Comments on “Deterministic AI: Why LLMs Aren't, and How to Build Products That Are Anyway”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
Thinking Machines ran one prompt through an open model 1,000 times at temperature 0 and got 80 distinct completions, with the outputs splitting at token 103 over a birthplace detail.
Why it ranked
No. 58 of 127 with a score of 0.64. The panel rated it highest on practical relevance (0.90) and reader interest (0.78), lowest on significance (0.57). The judges disagreed most on promotional (spread 0.53), so the story is marked contested. Placed No. 58, No. 48 by score alone: the 18th AI & machine learning story of the day (−0.080). The placement terms move stories; they are not part of the score.
- AI judgeJudge 2claude-haiku-5-5
- Practical, on-topic guide on LLM nondeterminism with cited evidence, but largely a vendor-flavored tutorial; the core finding is well known and the Jev claims are unverified.
- AI judgeJudge 3gpt-5.6-luna
- A practical, technically informed guide to LLM nondeterminism and product architecture, with cited studies and concrete testing advice. It includes vendor claims and conspicuous consultancy promotion, limiting substantiation and increasing promotional risk.
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 v2.3Contestedjudges differ by 0.53 on promotional
- Significance0.57
- Reader interest0.78
- Audience breadth0.75
- Practical relevance0.90
- Substantiated0.60
- Technical depth0.72
- New information0.77
- Counts against: Promotional0.36
- Counts against: Overclaim0.31
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) |
|---|---|---|---|---|---|---|---|
| SignificanceHow much does this change what people in tech know or can do? | 0.66 | 0.45 | 0.62 | 0.57 | 0.20 | +0.24 | +0.138 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.71 | 0.80 | 0.82 | 0.78 | 0.11 | +0.26 | +0.202 |
| Audience breadthHow many people who build technology does it concern? | 0.77 | 0.70 | 0.78 | 0.75 | 0.08 | +0.13 | +0.098 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.98 | 0.85 | 0.86 | 0.90 | 0.13 | +0.22 | +0.197 |
| 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. | 0.53 | 0.60 | 0.68 | 0.60 | 0.15 | +0.05 | +0.030 |
| Technical depthHow technically substantive is it? | 0.91 | 0.60 | 0.65 | 0.72 | 0.30 | +0.05 | +0.036 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.89 | 0.55 | 0.86 | 0.77 | 0.34 | +0.05 | +0.038 |
| 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. | 0.10 | 0.35 | 0.63 | 0.36 | 0.53 , above the contested threshold | −0.19 | −0.068 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.24 | 0.30 | 0.38 | 0.31 | 0.14 | −0.11 | −0.034 |
| Sum of contributions | +0.637 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.637 | ||||||
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.
<a href="https://rubric.hrih.si/editions/2026-10-30/58/"><img src="https://rubric.hrih.si/badge/2026-10-30/58.svg" alt="Ranked #58 on Rubric, 30 Oct 2026" width="245" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 1 pts, not on front page
Recorded for context only, checked 30 Oct 2026, 05:47 UTC. It played no part in the ranking.