Fetching from the wire…
01
02
03
04
05
06
07
08
Tools2026-09-25 · source-backed
agent.prevent_idle_sleep blocks idle system sleep during agent runs. (release) Same release adds BYOK for Opus 5.5 and GPT-6 Astra, Sol and Luna, SuperGrok sign-in, DeepSeek Flash 4.1, and better ACP compatibility. It won't stop a closed-lid sleep or a battery policy, so this covers one of two ways long unattended runs die on a laptop. I've lost runs to both.
Each link below shares sources, entities, or timing with this story.
GitHub published Project HydraFusion on September 4. Spotify published Portal on September 3. CodeRabbit published its Astra evaluation on September 4. None of them coordinated, and all three are the same argument. HydraFusion is a Copilot research preview that treats workflow...
July 9, across VS Code, Visual Studio, Copilot CLI, the cloud agent, github.com, GitHub Mobile, JetBrains, Xcode, and Eclipse. Sol is the high-reasoning tier at $5/1M in, $30/1M out, gated to Pro+/Max/Business/Enterprise. Terra is the balanced default at $2.50/$15. Luna is fas...
He argues the gains most likely come from training recipe and data, noting OpenAI's chief scientist saying compute depth stays within a factor of two of GPT-4. He walks through weight-reused looped stacks back to Universal Transformers (2018), with Nanbeige4.2-3B applying 22 b...
xAI released Grok 4.7 on September 21 on a new 2.1-trillion-parameter base, a 40% jump over Grok 4.6's 1.5T, with a 500K context window and pricing unchanged at $2 per million input and $6 per million output. Published scores: 46.3% on CursorBench 4.0 (up from 40.4%), 71.0% on...
OpenAI cut GPT-5.6 Luna roughly 80%, from $1 to $0.20 per million input and $6 to $1.20 output. Anthropic priced Opus 5 at $5/$25 per million, half of Fable 5. The trigger is DeepSeek, Zhipu's GLM-5.2 and Moonshot's Kimi K3 landing 60-90% below US flagship pricing, with DoorDa...
The Astra coverage went to price and context window. The number that changes how I'd deploy it went into a system card nobody read. Artificial Analysis measured GPT-6 Astra's hallucination rate on AA-Omniscience at 51% at max effort, against 92% for its predecessor. Accuracy w...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.