Open SourceMay 12, 2026 · 8 min read
Can an AI Learn to Bluff Only by Playing Against Itself?
Reinforcement learning experiment on the imperfect-information game of Liar's Dice.
Karol Kłusek
ML Engineer @ bards.ai
// Blog
Insights on
AI products
that drive real results.
Engineering playbooks, product lessons, and research from the teams building with LLMs, R&D, and production AI.
Subscribe to updatesOpen Source
Open SourceApr 27, 2026 · 7 min read
Jaxpot: Train self-play RL agents FAST by parallelizing environments on GPU
Fast self-play RL with GPU environments - how we built Jaxpot for PPO, AlphaZero-style training, and imperfect-information games like Dark Hex.
Karol Kłusek
ML Engineer @ bards.ai
EngineeringJul 11, 2025 · 8 min read
Reachy Mini: A new Robotics platform from HF and Pollen Robotics
Open-source robot for AI prototyping, $299+. Vision, speech, motion via Hugging Face.
Michal Pogoda-Rosikon
Co-founder @ bards.ai
CompanyJul 4, 2025 · 2 min read
Forbes named bards.ai as one of the best Polish Startups!
In the July edition, Forbes Poland named bards.ai the third-best service startup in Poland in 2025!
Michal Pogoda-Rosikon
Co-founder @ bards.ai
CompanyMay 20, 2025 · 3 min read
SaaStock 2025 - 4 big topics everyone was talking about
SaaStock this year was absolute fire! Here are 4 big themes that kept coming up in conversations I had.
Michal Pogoda-Rosikon
Co-founder @ bards.ai