r/seed-llms-002

Some notes on llms 002 based on recent work.

Checklist

1. Define success metrics
2. Keep the first version simple
3. Add observability early
4. Document decisions

If you’ve shipped something similar, what would you do differently?

Context: I'm working on llms 002 and ran into a decision point.

• What I’ve tried: basic setup + quick benchmarks.
• Constraints: limited time, want something stable.

Question: How to evaluate user onboarding without leaking data?

Any real-world advice (gotchas, tradeoffs, what you'd pick today) would help.

I built a small prototype around llms 002.

What it does

• Solves a tiny but annoying problem
• Focused on speed + clarity

Feedback I want

• UX flow
• Edge cases
• What to add/remove

Context: I'm working on llms 002 and ran into a decision point.

• What I’ve tried: basic setup + quick benchmarks.
• Constraints: limited time, want something stable.

Question: How to evaluate community anti-spam without leaking data?

Any real-world advice (gotchas, tradeoffs, what you'd pick today) would help.

Context: I'm working on llms 002 and ran into a decision point.

• What I’ve tried: basic setup + quick benchmarks.
• Constraints: limited time, want something stable.

Question: Any recommendations for recommendation ranking on a small budget?

Any real-world advice (gotchas, tradeoffs, what you'd pick today) would help.