AWS Built an Emulator for Everything. It Thinks Nobody Is Famous
Comments on “AWS Built an Emulator for Everything. It Thinks Nobody Is Famous”
Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked
AWS released AWS Emulator, a local stand-in for most of its services, built by autonomous agents with no human-written or human-reviewed code, according to AWS. Its public issues folder lists every gap found, and blogger Maish Saidel-Keesing's read-through shows the pattern: always-empty Rekognition celebrity results, Transcribe always returning en-US, and a 432,000-second TCP timeout against AWS's 350. About 121 open issues return real AWS hostnames, and permission checks are largely absent, so security tests may pass wrongly. The issue counts could not be verified.
Why it ranked
No. 7 of 137 with a score of 0.70. The panel rated it highest on reader interest (0.86) and practical relevance (0.76), lowest on new information (0.59). Placed No. 7, No. 15 by score alone: the placement terms moved other stories past it.
- AI judgeJudge 2claude-haiku-5-5
- Well-substantiated look at AWS emulator issue logs with concrete examples; humorous, heavy on AI-agent development and cloud testing, practical for builders, though much is entertainment and the piece is long.
- AI judgeJudge 3gpt-5.6-luna
- A substantial AWS emulator release is examined through concrete fidelity tests, issue statistics, agent workflow, and security caveats. It is highly actionable for cloud builders, though the core release was already covered and the tone occasionally overstates for humor.
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
0.70total under rubric v2.3
- Significance0.70
- Reader interest0.86
- Audience breadth0.71
- Practical relevance0.76
- Substantiated0.73
- Technical depth0.66
- New information0.59
- Counts against: Promotional0.10
- Counts against: Overclaim0.29
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? | 0.76 | 0.55 | 0.78 | 0.70 | 0.23 | +0.24 | +0.167 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.83 | 0.82 | 0.94 | 0.86 | 0.12 | +0.26 | +0.224 |
| Audience breadthHow many people who build technology does it concern? | 0.69 | 0.67 | 0.78 | 0.71 | 0.11 | +0.13 | +0.093 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.83 | 0.60 | 0.86 | 0.76 | 0.26 | +0.22 | +0.168 |
| 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. | 0.74 | 0.62 | 0.84 | 0.73 | 0.22 | +0.05 | +0.037 |
| Technical depthHow technically substantive is it? | 0.75 | 0.55 | 0.68 | 0.66 | 0.20 | +0.05 | +0.033 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.73 | 0.70 | 0.35 | 0.59 | 0.38 | +0.05 | +0.030 |
| 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. | 0.09 | 0.12 | 0.08 | 0.10 | 0.04 | −0.19 | −0.018 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.45 | 0.20 | 0.22 | 0.29 | 0.25 | −0.11 | −0.032 |
| Sum of contributions | +0.702 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.702 | ||||||
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/2026-11-13/7/"><img src="https://rubric.hrih.si/badge/2026-11-13/7.svg" alt="Ranked #7 on Rubric, 13 Nov 2026" width="238" height="28"></a>Claim check
Claim check: 5 matches source · 3 couldn’t check. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.
Couldn’t checkNumber
The AWS Emulator issues folder contains 19,252 issue files, of which 12,708 are fixed and 6,544 are still open.
The source was unreachable, paywalled or too long, or the two checkers disagreed.
The article says “19,252 issue files”
The source says No passage could be compared.
Source cited by the article: github.com/aws/aws-emulator/tree/main/issues
Couldn’t checkNumber
805 of the AWS Emulator issues are marked CRITICAL.
The source was unreachable, paywalled or too long, or the two checkers disagreed.
The article says “805 marked CRITICAL”
The source says No passage could be compared.
Source cited by the article: github.com/aws/aws-emulator/tree/main/issues
Couldn’t checkDate
All the AWS Emulator issues were filed between October 21 and November 10.
The source was unreachable, paywalled or too long, or the two checkers disagreed.
The article says “All filed between October 21 and November 10”
The source says No passage could be compared.
Source cited by the article: github.com/aws/aws-emulator/tree/main/issues
Matches sourceQuote
AWS's write-up says its team has not written or reviewed any of the emulator's code.
The cited source says the same thing.
The article says “Our team hasn’t written or reviewed any of the code”
The source says “Our team hasn’t written or reviewed any of the code”
Source cited by the article: aboutamazon.com/news/aws/how-autonomous-ai-agents-built-aws-emulator
Matches sourceNumber
An AWS agent produced a first version of SQS in about 15 minutes during the weekend experiment that started the emulator project.
The cited source says the same thing.
The article says “The agent came back with a first version of SQS in about 15 minutes”
The source says “Kiro came back after 15 minutes with a passable first version of an Amazon Simple Queue Service (Amazon SQS”
Source cited by the article: aboutamazon.com/news/aws/how-autonomous-ai-agents-built-aws-emulator
Matches sourceNumber
The emulator's Rekognition RecognizeCelebrities always returns an empty list, so every face is classed as unrecognized.
The cited source says the same thing.
The article says “The emulator always answers with an empty list. Every face goes into the “unrecognized” pile”
The source says “the handler answers HTTP 200 with CelebrityFaces unconditionally EMPTY for every image, and puts every detected face on the UnrecognizedFaces side instead”
Source cited by the article: github.com/aws/aws-emulator/blob/main/issues/things-that-do-not-work/20261106T074501Z-rekognition-recognizecelebrities-always-answers-an-empty-celebrityfaces-array-so.md
Matches sourceNumber
In the emulator, the default TCP established timeout is 432,000 seconds, whereas AWS says 350 seconds.
The cited source says the same thing.
The article says “AWS says 350 seconds. The emulator says 432,000 seconds”
The source says “A representative constant it emits regardless of type is networkInfo.connectionTrackingConfiguration.defaultTcpEstablishedTimeout = 432000 where AWS reports 350”
Source cited by the article: github.com/aws/aws-emulator/blob/main/issues/things-that-do-not-work/20261106T072955Z-ec2-describeinstancetypes-serves-an-emulator-authored-instance-type.md
Matches sourceNumber
Real AWS processes 500 campaigns in one Amazon Connect Campaigns batch request and only refuses at 501, though the API model says the maximum is 25.
The cited source says the same thing.
The article says “Real AWS happily processes 500”
The source says “recorded behavior is that a batch of up to 500 well-formed ids is PROCESSED structurally (each unknown id comes back in failedRequests, successfulRequests empty), and only 501 ids is refused”
Source cited by the article: github.com/aws/aws-emulator/blob/main/issues/things-that-now-work/20261029T172833Z-connectcampaigns-v1-validation-and-not-found-refusals-diverge.md
Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 4 pts, not on front page
Recorded for context only, checked 15 Nov 2026, 20:42 UTC. It played no part in the ranking.