Working on AI accelerators has made me appreciate abstractions a lot more.
An insane amount of thought and work gets hidden away so we can write a few lines of python and not care
RISC-V feels different because so much of the ecosystem is built in the open.
Open tools, open cores, public specs, random GitHub issues/forum threads.
Big appreciation for the open-source community making the architecture easier to experiment with 🙌
Can agents learn from past successes — without fine-tuning?
In our latest blog at Tile Labs, we test a simple idea: giving agents examples of successful past runs before they act. No weight updates. No retraining. Just better context.
What we found:
• More selective agents → fewer errors
• Smaller models improve the most
• Frontier models gain better calibration
Read more: https://t.co/7IvWA4f6AU
🚀 Our first blog is live: Benchmarking AI Agents using RL Environments
We evaluate frontier models and uncover a key insight — the gap between completing a workflow and completing it correctly is larger than you think.
Read more: https://t.co/Gh23BjKNjZ
We’re excited to introduce Tile Labs.
A research lab focused on advancing model intelligence — exploring how AI systems become more capable, adaptive, and autonomous.
More to come soon.
[email protected]