Prompt Engine
AI
llm routing
SHOW HN2024
How HN took it
0 positive, 4 neutral or asking, 0 mixed, 2 critical, out of 6 comments about the project. Thread score -0.22.
Idea: 0 for, 1 againstExecution: 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
Makers responded to criticism with detailed answers
From 1 comment
Hey swyk! I have a similar perspective when it comes to model routing and even LLM frameworks that centralize the schema when almost every provider already supports OpenAI's…
yoeven on HN
Objections
Model routing is unnecessary because people tune prompts to specific models
From 1 comment
congrats yoeven! i have been a skeptic of model routing like Martian, because while it sounds good in theory, 1) in practice, people tune prompts/behavior/output to models and…
swyx on HN
Router must be as smart as the strongest model, making it pointless
From 1 comment
congrats yoeven! i have been a skeptic of model routing like Martian, because while it sounds good in theory, 1) in practice, people tune prompts/behavior/output to models and…
swyx on HN
Labs will offer good-enough routing themselves
From 1 comment
congrats yoeven! i have been a skeptic of model routing like Martian, because while it sounds good in theory, 1) in practice, people tune prompts/behavior/output to models and…
swyx on HN
Homepage crashes with a client-side exception
From 1 comment
It's a pity your homepage crashes and replaces all content with the text ``` Application error: a client-side exception has occurred (see the browser console for more…
bosky101 on HN
Requests
Explain how the training dataset was annotated
From 1 comment
The small model you trained, how did you annotate the dataset? Because most of the times output from big models will be subjective, and with not a drastic difference in quality.…
ankit219 on HN
Publish the list of models used for training
From 1 comment
I can't find that list of hundreds of models to save my life... is it there some place?
soco on HN
Questions
How are prompt differences across model families handled
From 1 comment
I'd also ask how you're dealing with the idiosyncrasies across model families (its very different to prompt gemini vs claude vs gpt4o) when you are routing these lm inputs
htrp on HN
How the router was trained and annotated
From 1 comment
The small model you trained, how did you annotate the dataset? Because most of the times output from big models will be subjective, and with not a drastic difference in quality.…
ankit219 on HN
Alternatives named
Martian and other LLM routers
From 2 comments
congrats yoeven! i have been a skeptic of model routing like Martian, because while it sounds good in theory, 1) in practice, people tune prompts/behavior/output to models and…
swyx on HNHey swyk! I have a similar perspective when it comes to model routing and even LLM frameworks that centralize the schema when almost every provider already supports OpenAI's…
yoeven on HN