Top all-time · #2920
Harper Reed
Personal blog · harper.blogaiprogrammingproductivity
Harper Reed's personal blog at harper.blog covers ai, programming and productivity. Since 2024, 26 different Hacker News readers have linked it 27 times, most often “My LLM codegen workflow”. It is still writing: the last post was on 2026-09-22, and you can follow it by feed.
Too few sampled comments (14) to say how often HN recommends it.?
Why HN links it
HN readers link Harper Reed's LLM coding workflow: brainstorm a spec, plan it, then execute in discrete steps with tests and linters. It is valued as a practical guide to prompting coding models.
Summarised by Claude from a sample of 14 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Some writing by Harper Reed. Mostly about technology, politics, and things
Most-linked posts?
- My LLM codegen workflow15 people · 16 mentions · first linked 2025-02-18
- We Gave Our AI Agents Twitter and Now They're Demanding Lambos2 people · 2 mentions · first linked 2025-10-02
What Hacker News says?
Thanks for the concrete examples! These seem to be more sophisticated than the cases I use them for. Mostly I'm using them for tedious, simpler routine code (needing to process all files in a directory in a certain way, output them in a similar tree structure, with changes to filenames, logging, etc). Your Django ORM may be more complicated than the ones I use. I haven't tried it much with Django (still reluctant to…
Comment linking /2025/02/16/my-llm-codegen-workflow-atm/
on “Claude 4”Submitted My LLM codegen workflow as a story · 522 points
HN discussionhttps://harper.blog/2025/02/16/my-llm-codegen-workflow-atm/ "tl:dr; Brainstorm spec, then plan a plan, then execute using LLM codegen. Discrete loops. Then magic."
Comment linking /2025/02/16/my-llm-codegen-workflow-atm/
on “Claude 4”Submitted I accidentally built a meme search engine as a story · 319 points
HN discussionIs it something similar to Harper Reed's "My LLM codegen workflow atm"? https://harper.blog/2025/02/16/my-llm-codegen-workflow-atm/
Comment linking /2025/02/16/my-llm-codegen-workflow-atm/
on “Kiro: A new agentic IDE”Submitted We Gave Our AI Agents Twitter and Now They're Demanding Lambos as a story · 48 points
HN discussion> There's a significant blind-spot in current LLMs related to blue-sky thinking and creative problem solving. It can do structured problems very well, and it can transform unstructured data very well, but it can't deal with unstructured problems very well. While this is true in my experience, the opposite is not true. LLMs are very good at helping me go through a structure processing of thinking about architectural…
Comment linking /2025/02/16/my-llm-codegen-workflow-atm/
on “The highest quality codebase”Submitted Basic Claude Code as a story · 5 points
HN discussionHarper talks a lot about using defensive coding (tests, linters, formal verification, etc) so that its not strictly required to craft and understand everything. This article (and several that follow) explain his ideas better than this out of context quote. https://harper.blog/2025/02/16/my-llm-codegen-workflow-atm/
Comment linking /2025/02/16/my-llm-codegen-workflow-atm/
on “At Amazon, some coders say their jobs have begun to resemble warehouse work”Submitted I turned 600 meetings transcripts into a obsidian knowledge graph as a story · 4 points
HN discussionThis made the rounds recently: https://harper.blog/2025/02/16/my-llm-codegen-workflow-atm/ That quote really misrepresents his writing.
Comment linking /2025/02/16/my-llm-codegen-workflow-atm/
on “At Amazon, some coders say their jobs have begun to resemble warehouse work”Submitted We Gave Our AI Agents Twitter and Now They're Demanding Lambos as a story · 3 points
HN discussionThe trick for greenfield projects is to use it to help you design detailed specs and a tentative implementation plan. Just bounce some ideas off of it, as with a somewhat smarter rubber duck, and hone the design until you arrive at something you're happy with. Then feed the detailed implementation plan step by step to another model or session. This is a popular workflow I first read about here[1]. This has been the…
Comment linking /2025/02/16/my-llm-codegen-workflow-atm/
on “GitHub Copilot Coding Agent”Submitted My LLM Codegen Workflow as a story · 3 points
HN discussionIn no particular order: * experiment with multiple models, preferably free high quality models like Gemini 2.5. Make sure you're using the right model, usually NOT one of the "mini" varieties even if its marketed for coding. * experiment with different ways of delivering necessary context. I use repomix to compile a codebase to a text file and upload that file. I've found more integrated tooling like cursor, aider,…
Comment linking /2025/02/16/my-llm-codegen-workflow-atm/
on “The hidden cost of AI coding”Submitted Why Don't My Agents Break Containment? as a story · 2 points
HN discussionI have had Claude Code build authentication before successfully, following a pattern approximately like this: https://harper.blog/2025/02/16/my-llm-codegen-workflow-atm/
Comment linking /2025/02/16/my-llm-codegen-workflow-atm/
on “Firebase Studio”Submitted An LLM Codegen Hero's Journey as a story · 2 points
HN discussionOne blogpost I found on HN completely leveled up how I use LLMs for coding: https://harper.blog/2025/02/16/my-llm-codegen-workflow-atm/ Having the AI ask me questions and think about the PRD/spec ultimately made me a better system designer.
Comment linking /2025/02/16/my-llm-codegen-workflow-atm/
on “GPTs and Feeling Left Behind”Submitted Use an LLM to automagically generate meaningful Git commit messages as a story · 2 points
HN discussionNot OP, but if you are asking for your own reference or projects, I've found this "prompt flow" to be very effective: https://harper.blog/2025/02/16/my-llm-codegen-workflow-atm/ The reasoning models seem to respond quite well to the "ask me one question at a time, building on my previous answer" for the sake of coming up with a solid blueprint for the project, then build from there. I used this method to make a nice…
Comment linking /2025/02/16/my-llm-codegen-workflow-atm/
on “Show HN: Atari Missile Command Game Built Using AI Gemini 2.5 Pro”Submitted Getting Claude Code to do my emails as a story · 1 points
HN discussionSuper cool! I enjoyed reading Harper Reed's post too. For anyone, who hasn't seen it: https://harper.blog/2025/02/16/my-llm-codegen-workflow-atm/
Comment linking /2025/02/16/my-llm-codegen-workflow-atm/
on “Show HN: LLM-Tetris-A Classic Tetris Game in Go, 95% AI-Generated”Submitted Remote Claude Code: programing like it was the early 2000s as a story · 1 points
HN discussionAbout 6 months ago I became incredibly interested in game theory, especially as it relates to playing poker. Myself, a mediocre poker player, have only been playing for about a year. When I discovered that most online poker sites allow you to export your hand history, I was shook! Over the weekend, I built this site and got it online. It's massively scalable and HA. All the infra is in terraform. Everything is in Al…
Comment linking /2025/02/16/my-llm-codegen-workflow-atm/
on “I vibe coded AI agent to play poker”Submitted Waterfall in 15 Minutes or Your Money Back as a story · 1 points
HN discussionThere recently was a post by Harper Reed that goes into how to prepare the right prompts before you start coding with LLMs and break that down into smaller debuggable step. It might kill the vibe, but it keeps you in the drivers seat. https://harper.blog/2025/02/16/my-llm-codegen-workflow-atm/
Comment linking /2025/02/16/my-llm-codegen-workflow-atm/
on “Why Vibe Coding Is Killing Your Project”
