Hacker News: fhouser

New comment by fhouser in "How we index images for RAG"

fhouser — Tue, 02 Jun 2026 21:55:06 +0000

That's smart. Just the other day, I was thinking about how I would solve images/graphs/rich PDF stuff in a RAG system. Now I know more, thanks!

New comment by fhouser in "Ask HN: Does piping LLM output into a RAG stack sound like a good idea?"

fhouser — Mon, 30 Mar 2026 18:13:11 +0000

Not exactly agents ignoring instructions, but I'm wondering if (selective) inclusion of LLM responses in a RAG stack might be suitable as a sort of long-term memory for "accepted" LLM contributions to code for example. This way, unwanted novel or alternate solutions to repeated patterns might be avoided?

Ask HN: Does piping LLM output into a RAG stack sound like a good idea?

fhouser — Sat, 28 Mar 2026 02:02:00 +0000

I would like to know if this can improve agent memory or adherence to coding guidelines and policies in large codebases over time.

I'm also interested in this as a general concept.

Comments URL: https://news.ycombinator.com/item?id=47550791

Points: 2

# Comments: 2

New comment by fhouser in "Show HN: Optio – Orchestrate AI coding agents in K8s to go from ticket to PR"

fhouser — Thu, 26 Mar 2026 16:28:01 +0000

Yeah, I think that's the most important part in these new types of processes. Although it is tempting to just let an agent run with it for a while.

New comment by fhouser in "Show HN: Optio – Orchestrate AI coding agents in K8s to go from ticket to PR"

fhouser — Thu, 26 Mar 2026 14:44:03 +0000

The Hitchhiker's Guide to issue-tracking.

New comment by fhouser in "Show HN: Optio – Orchestrate AI coding agents in K8s to go from ticket to PR"

fhouser — Thu, 26 Mar 2026 14:38:41 +0000

Hot take: You should want to review your agents' output and progress.

New comment by fhouser in "Vibe Coding Is a Security Disaster That Is About to Happen"

fhouser — Sun, 22 Mar 2026 21:02:19 +0000

Thanks,that would be great.

New comment by fhouser in "Vibe Coding Is a Security Disaster That Is About to Happen"

fhouser — Sun, 22 Mar 2026 18:23:53 +0000

Opus 4.6 usually doesn't disappoint .. No double negative auth checks or race conditions to report on, but I can say that introducing new functionality and patterns mostly requires a few cycles before the "repeatable pattern" is cleanly documented in the spec. When bugs do come up, the agent is quite good at finding the root cause and implementing a fix.

New comment by fhouser in "Vibe Coding Is a Security Disaster That Is About to Happen"

fhouser — Sun, 22 Mar 2026 17:47:47 +0000

I recently shipped a "vibe-coded" project. You raise a good point: I hadn't considered the confidence gap. If it is true that LLM generated code produces more vulnerabilities in addition to there being more code overall, all while at the same time the developer feels better about their results, then that is concerning.

This is how I go about ensuring there is little to no chaos (your mileage may vary based on project size and characteristics): - Plan your project manually, do not outsource thinking to the LLM. This includes being intentional about architecture, tech-stack, dependencies, etc.. - I have planning, orchestrating, coding, and reviewing agents. These should be self-explanatory, but there's a catch: the workflow is automated. OpenCode allows you to define "subagents" which can be called by "primary" agents. I will write a detailed Gitlab issue that my planning agent can fetch and read. It will create a detailed resolution plan that I can point the orchestration agent to. The orchestrator then delegates implementation to one or more coding agents simultaneously. Results are in turn delegated to reviewer agents. If the reviewer agents don't complain, then the results are ready for human review in an MR. - Changes that pass all review are documented in the project spec. E.g., if new modules are added that require an auth guard pattern implementation that is already documented in the spec, they will be listed as relevant sites for that auth guard pattern, etc..

I feel like the LLM agents have been more thorough and consistent than I could have been without them. This goes for refactors too: Since the entire project is essentially mapped out in the spec.md file(s), it's hard for the agent to miss a relevant site in the code. Human review is key. Don't merge code you don't understand.

New comment by fhouser in "Show HN: Free online calculators built with AI"

fhouser — Sat, 21 Mar 2026 18:16:05 +0000

Do you have domain knowledge for each category in-house? How did you put together so many specific calculators while maintaining correctness in each calculator's respective domain?

Show HN: I built my first SaaS

fhouser — Sat, 21 Mar 2026 15:43:10 +0000

Hi everyone, second Submission, first SaaS, longtime HN reader.

TL;DR: This is a LinkedIn post generator.

If you are active on LinkedIn or other heavily text-based social media platforms, then you might find this interesting.

Bleeding edge technical highlights: - AI-SEO, or, "GEO": We use a so-called "grounding page" for presenting facts and non-facts about the website to help non-human readers "ground" themselves in the truth of the matter.

What I learned: - Agent-based coding is a massive boost and accelerator if you take the time to properly review results and keep everything on track.

Let me know what you think!

Comments URL: https://news.ycombinator.com/item?id=47468035

Points: 2

# Comments: 0

New comment by fhouser in "OpenCode – Open source AI coding agent"

fhouser — Sat, 21 Mar 2026 12:24:02 +0000

aider.chat was my entry to agentic coding. OpenCode followed. Not looking back.

Open standard for stable machine-readable facts for AI systems

fhouser — Fri, 20 Mar 2026 09:04:32 +0000

Article URL: https://groundingpage.com/

Comments URL: https://news.ycombinator.com/item?id=47452151

Points: 1

# Comments: 0