We benchmark LLMs at PostHog on practical tasks with real data
Comments on “We benchmark LLMs at PostHog on practical tasks with real data”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
PostHog describes how it benchmarks its LLM agents on real tasks, including its ReviewHog code review agent and Scouts, its scheduled research agent. It covers three evaluation approaches of rising complexity: checking against bugs from a single PR, a 33-incident golden set built from real past incidents, and tailored rubrics…
Why it ranked
No. 35 of 127 with a score of 0.67. The panel rated it highest on practical relevance (0.83) and technical depth (0.82), lowest on significance (0.54). Placed No. 35, No. 26 by score alone: the seventh 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
- Detailed, practical engineering write-up on benchmarking LLM agents with real data and isolation pitfalls. Strongly on-topic for builders; fairly substantiated by internal experiments, though it is a company blog with limited external verification.
- AI judgeJudge 3gpt-5.6-luna
- Detailed first-party engineering lessons on benchmarking agentic systems, grading subjective tasks, preventing state leakage, and building reproducible frozen environments, with concrete internal results and implementation tradeoffs.
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
0.67total under rubric v2.3
- Significance0.54
- Reader interest0.78
- Audience breadth0.64
- Practical relevance0.83
- Substantiated0.73
- Technical depth0.82
- New information0.76
- Counts against: Promotional0.13
- Counts against: Overclaim0.19
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? | 0.61 | 0.35 | 0.67 | 0.54 | 0.32 | +0.24 | +0.130 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.76 | 0.72 | 0.85 | 0.78 | 0.13 | +0.26 | +0.202 |
| Audience breadthHow many people who build technology does it concern? | 0.66 | 0.60 | 0.67 | 0.64 | 0.07 | +0.13 | +0.084 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.88 | 0.80 | 0.82 | 0.83 | 0.08 | +0.22 | +0.184 |
| 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. | 0.86 | 0.60 | 0.72 | 0.73 | 0.26 | +0.05 | +0.036 |
| Technical depthHow technically substantive is it? | 0.92 | 0.75 | 0.80 | 0.82 | 0.17 | +0.05 | +0.041 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.83 | 0.60 | 0.85 | 0.76 | 0.25 | +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. | 0.08 | 0.20 | 0.12 | 0.13 | 0.12 | −0.19 | −0.025 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.20 | 0.20 | 0.18 | 0.19 | 0.02 | −0.11 | −0.021 |
| Sum of contributions | +0.668 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.668 | ||||||
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/2026-10-30/35/"><img src="https://rubric.hrih.si/badge/2026-10-30/35.svg" alt="Ranked #35 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.