What control engineering taught me about building AI systems
In the years since, successful AI use cases became narrower and narrower and often required extensive engineering.Over the past few years, I worked as an AI engineer on a range of these kinds of projects. Some were successful, with hundreds of daily users; others never made it out of the prototype phase. This is the discipline of controlling systems such as drones.
- ▪In the years since, successful AI use cases became narrower and narrower and often required extensive engineering.Over the past few years, I worked as an AI engineer on a range of these kinds of projects.
- ▪Some were successful, with hundreds of daily users; others never made it out of the prototype phase.
- ▪This is the discipline of controlling systems such as drones.
Hacker News (AI / LLM) files mainly under ai. We currently carry 7,030 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 | Hacker News (AI / LLM) |
| Canonical URL | https://gerbenrijpkema.substack.com/p/what-control-engineering-taught-me |
| Publication time | Wed, 30 Sep 2026 15:01:45 +0000 |
| Retrieval time | 2026-09-30T15:12:01.887Z |
| Last seen | 2026-09-30T15:12:01.887Z |
| 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 | 5R2VcQtFyeVp · 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
What control engineering taught me about building AI systemsGerben RijpkemaSep 30, 2026ShareSince ChatGPT launched, one question has kept coming back: ‘Why can’t I just upload my files to ChatGPT and have it work?’ In the year after the release, almost every company wanted the same thing: an internal chatbot that was ‘ChatGPT, but it knows our data’. Most of these projects failed miserably. In the years since, successful AI use cases became narrower and narrower and often required extensive engineering.Over the past few years, I worked as an AI engineer on a range of these kinds of projects. Some were successful, with hundreds of daily users; others never made it out of the prototype phase.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Hacker News (AI / LLM).
Discussion
0 commentsMore from Hacker News (AI / LLM)
