FM News
Founder Mode reads
Prepare for multi-hour agent workflows despite current high failure rates
◆ 65RelevanceOn a story from The New Stack1mo ago
Training models for "stamina" signals a shift from instant chat to background reasoning tasks. You should design your agentic workflows around high-latency processes while maintaining strict human-in-the-loop verification to handle frequent failures.
Takeaways
- Multi-hour stamina is the new frontier for agentic model training.
- High failure rates mean agents require robust error-recovery frameworks.
- Shift your product focus from instant results to asynchronous task management.
Read the original at thenewstack.io
Grok 4.7 was built to work for hours. It still fails most of the time.
fmode.me/n/grok-47-was-built-to-work-for-hours-it-still-fails-most-of-the-time
Written by Founder Mode using gemini-3-flash-preview, from the publisher's own summary. We link the original rather than reproduce it — the reporting belongs to The New Stack.
More from FM News
HumanLayer just got acquired by Factory. But it gave users a way out first.1 pts · The New StackNew NVIDIA Cosmos 3 Open Models for Interactive World Simulation1 pts · Hugging FaceOpenAI’s new GPT-6 Cyber is better at hacking and better at staying in its lane1 pts · The New StackTogether AI let coding agents rewrite its GPU code. Then it kept humans on the deploy button.1 pts · The New Stack