Bonteq
Joined 6 years ago
Karma
5
Submissions
2
Member since
Jan 2
Joined 6 years ago
Location: Forestville, CA.
Remote: Yes
Willing to relocate: No
Technologies:
-- Python: Vanilla, Flask, Django, Selenium, Scrapy
-- Javascript: Vanilla, VueJS, NuxtJS, Vuex, Vuetify, CypressIO
-- Hosting: Heroku, Google Cloud Platform, Google Cloud Run, Pythonanywhere, Netlify
-- Docker
-- git
-- PostgreSQL
Résumé/CV: https://www.linkedin.com/in/cody-bontecou/
Email: [email protected]
The most obvious example here is `read` or `view_image`. If a multimodal model needs to read an image, it cannot use cat for that because the harness needs to inject the actual image payload into the protocol of the LLM.
Does your prototype overcome the limitations mentioned in the article?