my feeling is that stacking a dishwasher involves enough image processing and computer-use (or more realistically robotics) that it's a frontier model job rather than a 'write a program to do it' job
As we know from physics, even the most sophisticated mechanisms (e.g. friction) often ends up having a very simple model (proportional to the normal force).
Sooo, the score is maybe mostly just how much they fit?
Question for both: do you think that is also the case with a real-world dishwasher (it's mostly about getting stuff to fit), or do you think it's an issue with the current sim?
sure the code isn't hand-written and it's a work in progress, but it's designed to be modelled and calibrated around my own dishwasher so it's verifiably non-slop
Very cool and fun idea. This is a meta comment about the repo readme - there is an immense amount of what I would call ‘complaint smuggling’ / diffidence in the readme - basically Claude is uncomfortable about some of the claims vis a vis the status and embeds those negative feelings everywhere.
I suggest you have it scrub all of this from the readme; you’ll likely need to give it a few examples. It will improve readability a lot, and be less fatiguing to read. Plus if you scrub it all you won’t reprompt that attitude every time an agent reads the readme.
Btw I got Claude to give me the name “complaint smuggling” by giving it ten examples and asking it for a name. it’s an error pattern that’s so common I wanted to know what the model thought of it as - makes communicating about it really simple.
Composo is on a mission to ensure that AI transforms our world effectively, rapidly, and safely. Our platform squashes the legal and reputational risk associated with shipping AI apps and improves the helpfulness of our customer’s AI agents.
We believe subject matter experts are critical to evaluating and improving AI applications. Our platform equips them a powerful evaluation toolkit in a no-code interface, while giving engineers the development freedom they need to ship their best code.
We’re looking for generalist full stack software engineers, building up to a team of 5 over the coming months. Stack is Python FastAPI on Postgres with React Typescript frontend.
Send an email to luke[at]composo[dot]ai with your CV and a note about why Composo excites you. I will reply to all applications sent in September that clearly aren’t from bots.
