Agentic AI Foundation's September 28 MCP release finalizes stateless servers and bars removing deprecated features before July 2027. Teams moving servers off sessions now have a dated floor to plan migrations against.
Reality
- Evidence35
- Adoption
- Insufficient
- Hype gap+30
- Incentives55
- Confidence30
Flash's off-peak input price is under a quarter of what V4-Pro cost, and on DeepSeek's own table it beats the old Pro checkpoint on Terminal-Bench, but it scores 36.8 on Humanity's Last Exam and no V4.1-Pro has a date.
Reality
- Evidence42
- Adoption52
- Hype gap+30
- Incentives72
- Confidence40
Sol lists at $2 and $10 per million tokens and Luna at $0.10 and $0.50. The per-task savings OpenAI published come mostly from the lower price, and the cheaper tier scores below its predecessor on computer use.
Publishers:forkast.news · openai.com Reality
- Evidence55
- Adoption32
- Hype gap+30
- Incentives82
- Confidence62
A dev.to build runs two agents against one Convex API, one holding Kinde's default token and one rebuilding its token every two minutes. The client secret in the environment variable keeps the lifetime it always had.
Reality
- Evidence55
- Adoption
- Insufficient
- Hype gap+30
- Incentives55
- Confidence45
Removing initialize and Mcp-Session-Id lets MCP servers sit behind a plain round-robin load balancer. The handle pattern that replaces them keeps whatever authorizes the next call in the same buffer as attacker-controlled text.
Reality
- Evidence40
- Adoption18
- Hype gap+28
- Incentives45
- Confidence45
Speaker turns and end-of-speech markers now ride in the same token sequence as the words, which buys a cheaper pipeline and a tighter coupling than a three-vendor speech stack. The accuracy claim behind it is English-only.
Reality
- Evidence55
- Adoption24
- Hype gap+34
- Incentives72
- Confidence60
The access control vendor now takes risk signals from Microsoft Defender, CrowdStrike and SentinelOne to cut an AI agent's connection mid-session. The pitch rests on numbers it did not gather.
Reality
- Evidence24
- Adoption10
- Hype gap+46
- Incentives84
- Confidence33
A summary of work attributed to Google Research and MIT reports 180 controlled runs where multi-agent setups averaged +0.2% against one agent. The spread came from how agents were connected.
Reality
- Evidence15
- Adoption
- Insufficient
- Hype gap+65
- Incentives55
- Confidence45