Why use something which appears to have very similar results to tirzepatide/mounjaro but hasn’t been used by tens of millions on people without obvious issues like tirzep?
Does it use openrouter for model selection? Which models did you achieve the webarena result with? Are there any open source models which are any good for this?
For the WebArena result, we actually used a mixture of models checking each other's work and evaluating in real time. We found the verifications to be really effective in producing accurate results. Feel free to take a look at our architectural blog post to learn more in detail: https://blog.withmeka.com/introducing-meka-an-open-source-fr...
Unfortunately, we didn't try it out with open source models, but you are welcome to pull the repo and try with any model that has good visual grounding! (I heard UI-TARS and the latest Qwen visual model are quite good)
Im a doctor, i use LLMs a lot. Theyre great and generally better than the average doctor and will only get better. 90% of people on earth have pretty limited medical access. LLMs can give everyone access to at least great information and diagnosis, and hopefully in the future robots can give everyone access to to surgery and procedures too.
Use stairwaytogray, find a supplier with a history of many many 99+% purity reports from 3rd party testing sent to janoshik, then order 20 vials from that supplier, then either send a vial to janoshik yourself or participate in a group buy test (or just wait for someone else to test the same batch. At that point, it is very likely your ampoules have the same purity and amount. The best supplier seems to currently be sigma audley.
reply