gab_p_andrade Profile Banner
Gabriel P. Andrade Profile
Gabriel P. Andrade

@gab_p_andrade

Followers
96
Following
14
Media
0
Statuses
8

Researcher @GensynAI. Working on multi-agent RL, game theory, distributed learning, and decentralized ML.

Joined April 2025
Don't wanna be here? Send us removal request.
@gab_p_andrade
Gabriel P. Andrade
6 days
Formally verified judge models can settle markets or serve as a source of truth in other contexts. This has deep implications --> .1. Take the time to build an appropriately vetted (preferably open source) judge model for the usecase. 2. Design an appropriate prompt, set of.
@gensynai
gensyn
6 days
1/.Introducing Judge: Gensyn’s verifiable AI evaluation system. Traditional evaluators rely on closed APIs - opaque, silently updated, and impossible to reproduce. Judge executes a pre-agreed, deterministic AI model against real-world inputs & commits to be challenged in
2
5
21
@gab_p_andrade
Gabriel P. Andrade
27 days
RT @gensynai: 1/.Introducing BlockAssist: an AI assistant that learns directly from your Minecraft gameplay. Play it today and compete to….
0
124
0
@gab_p_andrade
Gabriel P. Andrade
29 days
RT @gensynai: 👉
Tweet media one
0
109
0
@gab_p_andrade
Gabriel P. Andrade
2 months
RT @gensynai: What is Gensyn?
0
87
0
@gab_p_andrade
Gabriel P. Andrade
2 months
RT @_grieve: Ultra-high scale reinforcement learning is one of the best pathways for pushing the frontier of machine intelligence. @gensyna….
0
10
0
@gab_p_andrade
Gabriel P. Andrade
2 months
RT @gensynai: 1/.Introducing RL Swarm’s new backend: GenRL. A modular reinforcement learning library built for distributed, fault-tolerant….
0
73
0
@gab_p_andrade
Gabriel P. Andrade
2 months
RT @gensynai: Introducing CheckFree. A fault tolerant method for decentralised training, with no checkpoints or redundant compute. Up to 1….
0
66
0