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.
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
- 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).
| 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? | 0.35 | 0.35 | 0.48 | 0.40 | 0.13 | +0.24 | +0.095 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.40 | 0.80 | 0.72 | 0.64 | 0.40 | +0.26 | +0.166 |
| Audience breadthHow many people who build technology does it concern? | 0.61 | 0.60 | 0.62 | 0.61 | 0.02 | +0.13 | +0.079 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.74 | 0.75 | 0.72 | 0.74 | 0.03 | +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. | 0.87 | 0.60 | 0.82 | 0.76 | 0.27 | +0.05 | +0.038 |
| Technical depthHow technically substantive is it? | 0.90 | 0.80 | 0.68 | 0.79 | 0.22 | +0.05 | +0.040 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.85 | 0.30 | 0.90 | 0.68 | 0.60 , 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. | 0.07 | 0.03 | 0.03 | 0.04 | 0.04 | −0.19 | −0.008 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.26 | 0.10 | 0.08 | 0.15 | 0.18 | −0.11 | −0.016 |
| Sum of contributions | +0.591 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.591 | ||||||
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.
<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
Recorded for context only, checked 11 Nov 2026, 05:47 UTC. It played no part in the ranking.