Tag
Forge '26, hosted by Fireworks AI on November 3rd in San Francisco, is billed as one of the biggest AI events of the year, featuring fireside chats with NVIDIA's Jensen Huang and DHH plus a keynote from Fireworks CEO Lin Qiao. The free, application-only event focuses on how top teams choose models, design evals, serve them, and route requests in production.
LangChain and Fireworks are hosting a hands-on workshop on August 25th to teach participants how to train custom evaluation models for AI systems, followed by a happy hour. The workshop focuses on building reliable eval models to optimize agent performance in LangSmith.
Increased drone surveillance by police and fire departments during July 4th celebrations led to significant fines, including a $100,000 citation, as part of a broader trend of using drones to deter illegal fireworks.
The International Space Station orbited over Los Angeles on July 4th, with the city's fireworks visible from space as America celebrated 250 years of independence.
Factory's Droid Shield 2.0 uses two small post-trained models for secret detection, outperforming GPT-5.5 and Opus 4.8 on this task while being faster and cheaper.
GLM 5.2, an open AI model, is now available in the Cursor coding tool via a partnership with Fireworks.
LangChain and Fireworks fine-tuned a Qwen model to detect 'Perceived Error' from agent traces, achieving 100x cost reduction while maintaining frontier performance. The judge model is designed to enrich traces with error signals for monitoring agentic systems.
A joint study by LangChain Labs and Fireworks AI demonstrates fine-tuning an open Qwen model to create a trace judge that detects 'perceived error' in production traces, achieving frontier performance at up to 100x lower cost. The model is evaluated on two internal datasets and shows generality across applications.