Top all-time · #23097
Colin Harman
Personal blog · colinharman.substack.com · on HN as clharmanaiprogramming
Colin Harman writes Retrieve and Generate, a personal blog at colinharman.substack.com about ai and programming. Since 2023, 3 different Hacker News readers have linked it 7 times, most often “Use Cases for Enterprise LLMs”. It is still writing: the last post was on 2025-06-26, and you can follow it by feed.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
HN readers discuss this post's side-by-side comparison of vector databases, including its claim about PGVector and Chroma developer experience. The one comment pushes back on that claim from hands-on experience.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Insights on building with Large Language Models in the enterprise.
Most-linked posts?
- Use Cases for Enterprise LLMs2 people · 2 mentions · first linked 2023-09-23
- /p/beware-tunnel-vision-in-ai-retrieval2 people · 2 mentions · first linked 2023-09-14
What Hacker News says?
@rafaelero I'm working on a blogpost ( https://colinharman.substack.com/ ) to demonstrate this fact since I get a lot of tiresome questions like "why don't you just train instead of retrieving" Do you have any scripts you could share for the training/eval process? Would love to credit you in the post
Comment linking /
on “You probably don’t need to fine-tune LLMs”Submitted With LLMs, enterprise data is different as a story · 4 points
HN discussionStrongly disagree with PGVector's DX being worse than Chroma. Installing, configuring, and working with Chroma was infuriating -- it's alpha software and has the bugs and rough edges to prove it. The tools to support and interface with postgres are battle-tested and so much nicer by comparison; getting Chroma working took over a week, ripping it out and replacing with PGVector took a couple hours. Also agree with th…
Comment linking /p/beware-tunnel-vision-in-ai-retrieval
on “Choosing vector database: a side-by-side comparison”Submitted Self-Improving CLI Agents in 5 minutes as a story · 3 points
HN discussionYou need a vector db because all the vector db companies need customers... You definitely do need information retrieval. It just shouldn't be limited to vector dbs. Unfortunately vector db companies and the VCs that back them have flooded the internet with propaganda suggesting vector db is the only choice. https://colinharman.substack.com/p/beware-tunnel-vision-in-a... For most serious use cases, you'll have far to…
Comment linking /p/beware-tunnel-vision-in-ai-retrieval
on “A Comprehensive Guide for Building Rag-Based LLM Applications”Submitted Use Cases for Enterprise LLMs as a story · 1 points
HN discussionSubmitted Use Cases for Enterprise LLMs as a story · 1 points
HN discussion