System Prompt Learning
AI
prompt optimization
SHOW HN2025
How HN took it
0 positive, 3 neutral or asking, 0 mixed, 2 critical, out of 5 comments about the project. Thread score -0.25.
Execution: 0 for, 1 againstIdea: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Related case-based reasoning work and similar projects are worth looking at
From 2 comments
You should take a look at something called Case-based reasoning. Seems to perfectly fit into the road you are currently walking, as you basically just rediscovered the CBR-cycle.
imaltont on HNThis is a really cool idea! I recently came across another project on GitHub: https://github.com/tensorzero/tensorzero that explores a similar direction. You might find it…
tanchaowen84 on HN
Objections
Benchmark baseline unclear; generic strategies might work as plain prompt additions
From 1 comment
That's an interesting space to explore! I'm wondering about the baseline in the benchmarks. Which prompts did you use for those? I'm asking because some of the resulting prompts…
yunusabd on HN
Unbounded strategy growth is a scaling concern
From 1 comment
How do you forsee a system like this efficiently managing and relying on a set of strategies whose size can become unbounded?
Falimonda on HN
Claimed re-reading strategy may not match the paper's method
From 1 comment
Okay, but it looks like in the paper, they are actually adding the question twice in the prompt, not just instructing the model to read it twice. Or am I missing something?
yunusabd on HN
Requests
Show input/output examples
From 1 comment
I would like to see some interesting input/output pairs. Do you have any?
ramonga on HN
Measure which prompt parts contribute most to gains
From 1 comment
That's an interesting space to explore! I'm wondering about the baseline in the benchmarks. Which prompts did you use for those? I'm asking because some of the resulting prompts…
yunusabd on HN
Questions
What happens when a user manually edits a strategy in learning mode
From 1 comment
If I jump in and, say, manually 'tweak' one of those JSON strategies because I think I have a better idea, what happens next? Does the LLM just roll with my brilliant human…
dedicate on HN
Which baseline prompts were used in the benchmarks
From 1 comment
That's an interesting space to explore! I'm wondering about the baseline in the benchmarks. Which prompts did you use for those? I'm asking because some of the resulting prompts…
yunusabd on HN
Alternatives named
TensorZero
From 1 comment
This is a really cool idea! I recently came across another project on GitHub: https://github.com/tensorzero/tensorzero that explores a similar direction. You might find it…
tanchaowen84 on HN
Case-based reasoning
From 1 comment
You should take a look at something called Case-based reasoning. Seems to perfectly fit into the road you are currently walking, as you basically just rediscovered the CBR-cycle.
imaltont on HN