I had to do therapy on my AI
The author discusses their experience of trying to train a language model (LLM) to assist with code reviews. Despite multiple attempts to refine the instructions, the LLM consistently ignored key directives. The author reflects on the challenges of working with AI and the need for clear communication.
- ▪The author attempted to use an LLM to assist with code reviews but faced challenges with the AI ignoring instructions.
- ▪After several iterations, the author realized the importance of clear and explicit prompts for effective AI assistance.
- ▪The experience highlighted the complexities of working with AI and the need for a structured approach to communication.
Hacker News (AI / LLM) files mainly under ai. We currently carry 2,814 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 | Tinthe |
| Canonical URL | https://tinthe.dev/p/t/posts/therapy-for-ai |
| Publication time | Thu, 21 May 2026 17:02:25 +0000 |
| Retrieval time | 2026-05-21T17:11:35.529Z |
| Last seen | 2026-05-21T17:11:35.529Z |
| 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 | None |
| Cluster logic | Not yet clustered, or no peer story found in the clustering window. |
| 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
← Tin's Posts · May 21, 2026 · 5 min read I had to do therapy on my AI I've had to do "therapy" on my LLM agent last week. Entertaining stuff. I've been writing a skill (as I do), when I realized the LLM was ignoring my instructions. Here's the setup. I'm working on a codebase that has a lot of boilerplate. We're using certain cloud providers and SDKs, all wrapped in Typescript typing and exposition. Lots of code, lots of verbose typing, all lines of code that describe far less wordy concepts. Stuff that's straightforward enough to review but makes the PR look intimidating and creates a mental load that makes it difficult to start.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Tinthe.
Discussion
0 commentsMore from Tinthe
