The 2 Days my AI Assistant built a government instead of training a model
An approval literally said GO while its own findings described reasons not to go. Before launching, the wrapper reran a large ceremonial test suite. It completed the entire review.This was it.After two days, dozens of protocol versions and enough tests to establish asmall sovereign nation, we had reached the finish line.Me: “So we have the second approval?”AI: “No.”Me: “Did the reviewer fail?”AI: “No.
- ▪An approval literally said GO while its own findings described reasons not to go.
- ▪Before launching, the wrapper reran a large ceremonial test suite.
- ▪It completed the entire review.This was it.After two days, dozens of protocol versions and enough tests to establish asmall sovereign nation, we had reached the finish line.Me: “So we have the second approval?”AI: “No.”Me: “Did the reviewer
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,445 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Medium |
| Canonical URL | https://medium.com/@cmitre/the-two-days-my-ai-assistant-built-a-government-instead-of-training-a-model-a22e42430019 |
| Publication time | Tue, 11 Aug 2026 13:55:04 +0000 |
| Retrieval time | 2026-08-11T14:05:44.224Z |
| Last seen | 2026-08-11T14:05:44.224Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 1ai9wlDTg3zd · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Artificial IntelligenceAI AgentSoftware EngineeringMachine LearningHumorThe Two Days My AI Assistant Built a Government Instead of Training a ModelChris Mitre7 min read·Just now--ListenShareWritten by Chris MitreLet me tell you about the two days my AI assistant spent trying to obtainpermission from itself.The original job involved preparing something for a machine-learning pipeline.At least, I think it did.By the second day, nobody appeared to be working on that anymore.We had independent reviewers.Frozen evidence.Signed approvals.Sealed secrets.One-shot execution ceremonies.Hundreds of tests.And an increasingly serious constitutional dispute about whether one tiny subprocess was allowed to exist.I had asked an AI assistant to make the work safe.The AI assistant built a government.– -THE…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Medium.