Edition of Wednesday 11 November 2026

A simple Python implementation of the ReAct pattern for LLMs

Comments on “A simple Python implementation of the ReAct pattern for LLMs”

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

Simon Willison published a minimal Python implementation of the ReAct pattern, which lets an LLM alternate between reasoning and calling external tools such as Wikipedia search, a blog search, and a calculator, with results fed back into the conversation.

Read the original at til.simonwillison.net. 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. 107 of 143 with a score of 0.59. The panel rated it highest on technical depth (0.79) and substantiated (0.76), lowest on significance (0.40). The judges disagreed most on new information (spread 0.60), so the story is marked contested. Placed No. 107, No. 97 by score alone: the 44th 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, concise tutorial building ReAct-style tool use on ChatGPT in ~50 lines of Python; useful to builders, substantiated by runnable examples, though the pattern is already widely known and the code is admittedly rough.
AI judgeJudge 3gpt-5.6-luna
A concise, reproducible implementation showing how LLM tool use works, with executable code and useful safety caveats. It is technically relevant and novel relative to the comparison list, but remains a rough, small-scale prototype.

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

0.59total under rubric v2.3Contestedjudges differ by 0.60 on new information

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.40
  • Reader interest0.64
  • Audience breadth0.61
  • Practical relevance0.74
  • Substantiated0.76
  • Technical depth0.79
  • New information0.68
  • Counts against: Promotional0.04
  • Counts against: Overclaim0.15

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?0.350.350.480.400.13+0.24+0.095
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.400.800.720.640.40+0.26+0.166
Audience breadthHow many people who build technology does it concern?0.610.600.620.610.02+0.13+0.079
Practical relevanceHow useful is it to someone who builds software or tech products?0.740.750.720.740.03+0.22+0.162
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.0.870.600.820.760.27+0.05+0.038
Technical depthHow technically substantive is it?0.900.800.680.790.22+0.05+0.040
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.850.300.900.680.60 , above the contested threshold+0.05+0.034
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.0.070.030.030.040.04−0.19−0.008
OverclaimDo the headline or conclusions claim more than the body supports?0.260.100.080.150.18−0.11−0.016
Sum of contributions+0.591
Claim-check penalty0.000
Total, as published0.591

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 #107 on Rubric, 11 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-11/107/"><img src="https://rubric.hrih.si/badge/2026-11-11/107.svg" alt="Ranked #107 on Rubric, 11 Nov 2026" width="252" 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 11 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 “A simple Python implementation of the ReAct pattern for LLMs”

More on Rubric

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

  1. Score 0.75

    llama.cpp v1.0