Wednesday at 12pm ET - join @semihsmile in talking through the recently published paper:
"The Role of Feedback Alignment in Self-Distillation"
Links in the thread below.
https://t.co/Cy3QiYfotW
Plots + full details in the blog post and paper:
✍️ https://t.co/uYq1vdUjrC
📜 https://t.co/03AAEaUloV
Also, visit our poster at the ICML 2026 Workshop on RL from World Feedback (RLxF)!
Multi-agent LLM systems are everywhere, and agents talk to each other: critiquing, correcting, giving feedback.
A design lever: what style of agent-to-agent communication works best?
At @gensynai, we designed one. New style, same agents, better results.
https://t.co/uYq1vdUjrC
The headline: feedback alignment matters as much as feedback quality.
As agent-to-agent transcripts become a dominant data type, how agents phrase feedback to each other is a training-signal design choice.
Prediction markets are sold as epistemic infrastructure. In practice, they often have little utility beyond entertainment. The usual story blames the crowd, but that narrative gets it backwards.
We introduce evidence markets; a mechanism for eliciting more than just a price. 🧵
Introducing Evidence Markets
A new market mechanism where you can trade not just a prediction, but also the evidence behind your prediction.
The majority of prediction market volume is sports betting but the real value is info elicitation. Evidence markets make this explicit.
Today at @gensynai, we are introducing DEI: Diversity in Evolutionary Inference.
A system where different AI models work together to solve problems instead of running thousands of copies of the same model.
https://t.co/GWMntroD0r
New research from @oguzer90 has been published:
F-TIS: Heterogeneous GRPO Without Homogeneous Assumptions
"Participants no longer need to run identical models or train the same parameter subsets to contribute useful RL experience."
Read via the links below.
Coming soon: $AI
@gensynai, the network for machine intelligence, is an open infrastructure layer for AI. It provides infrastructure AI needs to operate at scale: compute, data, and information exchange.
Get ready → https://t.co/THPTuVQs1e
Stop multitask training. Just DUME.
Today, we introduce a training-free way to turn multiple domain experts into a single multi-domain model. DUME is training-free, scalable, and cheap.
https://t.co/MFdpsSO3fL
When you run the same AI model with the same inputs twice, you'd expect the same output.
But modern GPU execution is optimised for speed, not fixed ordering, and existing determinism tools do not solve this across hardware.
Today we're changing that.
https://t.co/wIVL5mCvBO
Prediction market infrastructure requires scalable, decentralised ML systems.
Here's a look at the upgraded version of Delphi app for the @GensynFND Mainnet launch with the following features: REE, Dynamic-PM, and user-created markets. 🧵
the @GensynFND mainnet will launch in April, with the $AI token distributed and available on exchanges
the @gensynai vision is to scale machine intelligence, we do that by building primitives and using them in apps like Delphi
mainnet will launch with huge changes to Delphi 🧵