Agents
Getting an agent to frontier quality is one problem. Serving it efficiently is another. Nate Yohannes, President of Data & AI Labs at @Zeta…
Getting an agent to frontier quality is one problem. Serving it efficiently is another. Nate Yohannes, President of Data & AI Labs at @ZetaGlobal, and Sardhendu Mishra, Lead AI Engineer, covers fine-t
Getting an agent to frontier quality is one problem. Serving it efficiently is another. Nate Yohannes, President of Data & AI Labs at @ZetaGlobal, and Sardhendu Mishra, Lead AI Engineer, covers fine-tuning for both at Fireworks Forge. Can’t make it to SF? Register for the keynote livestream: https://bit.ly/forgelivex
Related
- Open + closed models = better together. Our previous research with @harvey showed the benefits of combining a frontier closed model as an ad…
- Can a small fine-tuned model, routing across open models, beat a solo closed frontier model on an agentic task? We'll build it end to end w…
- If you want frontier-level coding and agent performance but you don't want to pay closed-model prices, GLM 5.2 is the open model you've prob…
- Why A Frontier Data Agent Outperforms General Coding Agents in Quality and Cost
- Independent numbers from @ValsAI. Fewer tokens per turn means lower cost and faster agent loops on every call. Try Ember-1 on Fireworks Serv…
Source: Fireworks AI (X) | 2026-10-29