Blatant-Why: Stop paying for AI agent wrappers, start asking what's underneath(github.com)
github.com
Blatant-Why: Stop paying for AI agent wrappers, start asking what's underneath
https://github.com/001TMF/blatant-why
3 comments
Very interesting, just had a look at the repo. According to the technical report, Latent-Y is a frontier LLM with access to bio tools, databases, and literature, which orchestrates its Latent-X2 model. It can even write its own computational tools on the fly. Architecturally, it's LLM + tool use, same pattern as Claude Code with MCP and skills. BoltzGen achieves a 66% VHH target-level success rate on novel targets, compared to Latent-Y's 67%. So, conceptually orchestrating boltzgen for VHH design with some bioinformatics wouldn't be too different.
Latent Labs (a $200M company) launched an "autonomous AI agent for drug design" that appears to wrap open-source models behind a paywall. Tristan Farmer built an alternative with Claude Code in a day and has interesting things to say about it: https://www.linkedin.com/posts/tristan-farmer-973b7a17a_anti...
Unrestricted link: https://web.archive.org/web/20260325194514/https://www.linke...
Unrestricted link: https://web.archive.org/web/20260325194514/https://www.linke...