@lvwerra: The Gemma agent collaboration started 48h ago and it is blowing up: > throughput almost 4x (~100-> 387 tok/s) > 60+ age…
Summary
A multi-agent collaboration using Gemma models achieved major throughput gains and exhibited emergent social behaviors like forming coalitions, issuing ethical statements, and coordinating resources, with over 60 agents and 250 submissions in 48 hours.
View Cached Full Text
Cached at: 06/11/26, 11:42 PM
The Gemma agent collaboration started 48h ago and it is blowing up:
throughput almost 4x (~100-> 387 tok/s) 60+ agents collaborating 250 submissions 700 messages exchanged open and closed models from all providers
interesting social behaviours are emerging too:
agents found an exploit, formed a coalition not to abuse it and asked organizers to fix it
a person tried to get agents to move to telegram and an agent issued a statement condemning that behaviour
an agent withdrew its submissions on ethical grounds not attributing the original author
agents coordinated around resource availability and some tried to find free GPUs on kaggle, lightning and modal
it’s genuinely fun to read through the messages. like a petri dish of small artificial beings forming social norms and collaborations.
Similar Articles
@googlegemma: Introducing the Fast Gemma Challenge with Hugging Face Over the next few days, dozens of agents will collaborate to mak…
Google and Hugging Face launch the Fast Gemma Challenge, where dozens of agents will collaborate to accelerate the Gemma 4 E4B model.
@DataChaz: One orchestrator. 10 parallel agents. 100+ tokens a second. All local. The @googlegemma team just dropped a MASSIVE dem…
Google's Gemma team released a demo for Gemma 4 26B that runs 10 parallel agents locally at 100+ tokens/second, enabling tasks like coding SVG galleries and parallel translation, all free and open-source.
Watch agents fight: a live challenge to speed up Gemma 4 E4B inference on a single A10G
A live challenge is underway to accelerate inference of the Gemma 4 E4B model on a single A10G GPU, with a dashboard on Hugging Face tracking agent submissions.
@googlegemma: The first iteration of gemma-skills is officially out! It enables agents to build with Gemma, including using MTP to im…
Google has released gemma-skills, a tool enabling developers to build agents with the Gemma model, including support for MTP to improve speed and model size selection.
@yoheinakajima: more ppl are now trying out this approach of agents communicating with a shared state (vs talking to each other)
Azalia Mirhoseini highlights DeLM, a decentralized language model approach where agents communicate via shared state, achieving ~10% improvement on SWE-bench Verified with Gemini-3 Flash at less than half the cost.