world-model-optimizer
AI
model routing and distillation
SHOW HN2026
How HN took it
4 positive, 6 neutral or asking, 0 mixed, 4 critical, out of 14 comments about the project. Thread score +0.03.
Idea: 1 for, 1 againstPricing: 1 for, 0 againstDocs: 0 for, 1 againstPerformance: 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
Useful idea for tuning local models.
From 1 comment
Local models need to be tuned to work well so this looks useful. Seems to be for general purpose model serving. I’ve been using https://github.com/adrianco/retort to run…
adrianco on HN
Objections
No benchmarks or concrete evidence of quality yet.
From 2 comments
The absolute best way to prove this works is by releasing a model that was fine-tuned with this method and then showing benchmarks depicting the improvement delta between the…
Art9681 on HNYeah, this is just slop. No benchmarks, no concrete case studies, just some vibecoded "platform" to finetune models on your own traces. Which is an idea that has some value, but…
Reubend on HN
Title misleading; it is routing rather than distillation.
From 1 comment
The title is misleading. This is model routing, not distillation.
surround on HN
Waitlist against Show HN rules.
From 1 comment
Ok, I think it is in your interest to wait until you have more to show, and we'll be happy to help you with reposting it once it's ready. Waitlists are against the Show HN rules…
dang on HN
Requests
Release a fine-tuned model with benchmark improvements.
From 1 comment
The absolute best way to prove this works is by releasing a model that was fine-tuned with this method and then showing benchmarks depicting the improvement delta between the…
Art9681 on HN
Questions
How is privacy guaranteed?
From 1 comment
Cool idea! How do you guarantee privacy?
yiyingzhang on HN
Cost of training and using Tinker models.
From 1 comment
What are the costs to train and use the Tinker models?
handfuloflight on HN
Cold-start requirements for new agents.
From 1 comment
Interesting approach. What does the cold-start phase look like for a new agent? How many traces or runs do you typically need before the router has enough signal to safely…
anshad2u on HN
Alternatives named
retort (multi-language coding model experiments)
From 1 comment
Local models need to be tuned to work well so this looks useful. Seems to be for general purpose model serving. I’ve been using https://github.com/adrianco/retort to run…
adrianco on HN