FM News
Founder Mode reads
Prepare for multi-hour agent workflows despite current high failure rates
◆ 65RelevanceOn a story from The New Stack1h 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
TypeSafe launched Jev because sequential LLMs are “totally useless for computers”1 pts · The New StackYour AI agent is burning tokens on choices that don’t need words1 pts · The New StackAWS open-sources an AI agent it says is 45% cheaper than Claude Code and Codex1 pts · The New StackMeta’s AI agent has been blocked from using Amazon.com1 pts · TechCrunch AI