AgentFlareSocial Pulse · Tech · 2026-10-21 20:50 UTC
@NousResearch: Agents and the claim that software is done
Jensen closed his GTC Berlin 2026 keynote with this Hermes Agent demo as the finale. He introduced it by saying the way to build an agent is to ask an agent to build it for you, so he installed and…
You're reading the full report — free for humans and search engines.
The same content ships as a structured JSON dataset (normalized facts, sources and
citation arrays, no HTML parsing) so AI agents can consume it directly — metered per fetch via the open
HTTP 402 payment protocol.
crawlerAutoPrice=true · verify at https://esa.aisa.one/api/v1/access/verify
Jensen closed his GTC Berlin 2026 keynote with this Hermes Agent demo as the finale. He introduced it by saying the way to build an agent is to ask an agent to build it for you, so he installed and set up a customized Hermes in one prompt. Then he used Hermes, running on @nvidia RTX Spark, to create a simulated training environment for the @huggingface Microduck. Hermes planned an obstacle course with Nemotron and had GPT-6 Astra build it using FreeCAD, Omniverse libraries, Blender, Newton, and Isaac Lab. Hermes trained thousands of simulated ducks on that course until the validated policy was ready to run on the real robot in the physical world. At Nous, we believe open source is a practical tool as much as a philosophical ideal. It gives users the ability to build powerful, complex workflows chaining numerous local+cloud models, devices, and tools themselves instead of waiting for a company to enable them.
Part of the conversation: Agents and the claim that software is done
@MatthewBerman posts 'Reverse Engineer Anything' and says 'Software is done', with 39.2K likes and 3.9M views. @NousResearch says Jensen closed his GTC Berlin 2026 keynote with a Hermes Agent demo, in which one prompt set up a customized Hermes. It then planned an obstacle course and trained simulated ducks for the @huggingface Microduck robot. Nous argues open source lets users chain local and cloud models themselves.
Why it mattersBoth posts present agents as building complex things from a prompt, and the first drew the highest like count in this set.
Other posts in this conversation
Reverse Engineer Anything 😂 Software is done. https://t.co/XyUfCymB9b
How it compares
This post ranks #7 of the 14 highest-engagement tech posts AgentFlare tracked on 2026-10-23, with 1.0× the median likes. See the full Tech briefing.
How this page is made. Post text and engagement come from the AISA Twitter API (advanced search, top results). Conversation summaries are written from the post texts only; a post is the author’s claim, not a verified fact.
Sources & citations
- @NousResearch on X 2026-10-21 20:50 UTC
- AISA Twitter API