Ashlr Brief.

OpenAI launched GPT-6.1 Terra, a mid-tier model for computer use and visual reasoning tasks. It costs roughly half as much as GPT-5.6 Terra while running faster on agent workflows.

Overnight into October 27, Phantom began recording each run's routing decision, Ashlr Stack added a merge-queue gate, and ashlr-plugin raised its MCP SDK floor.

October 26 brought releases of Locus 0.5.2, Ashlr Stack 0.2.2 and ashlr-plugin 1.37.1, plus opt-in routing in Phantom that tries local models first.

OpenAI released GPT-6.1 Terra, a fast model for computer use and everyday work at $1 per million input tokens and $5 per million output tokens.

On October 25 Phantom added signed run receipts, and Ashlr's tools learned a shared handshake so each one's doctor can find and repair the others.

Jack Dorsey’s Block introduced Dessa, a speech-to-speech model trained only on human conversation. It runs locally on high-end Macs and is entering limited safety researcher access.

Claude Duet is a research preview for US Pro and Max subscribers through a waitlist. Anthropic says it briefs users and works across connected apps.

IBM’s ALTK-Evolve turns past agent runs into a playbook. IBM reports more consistent support-task results, with higher input-token costs.

Mistral’s Voxtral 3 combines speech, reasoning and tools. API hosting and self-deployment need different checks before a live pilot.

Meta published Muse Glimmer 30B under Apache 2.0. It is built to plan, call tools and recover from failures on one consumer GPU, without the cloud.

Claude Code and Cursor change how agents run, OpenAI discloses four more incidents, Replit makes OpenAI its default, and a paper breaks agent loops.

Start with a small task, choose how closely to steer it, and learn the few Phantom terms that matter before connecting an account.

What changes when an agent keeps working after you leave? A plain-English guide to goals, signed permissions, shadow runs and the evidence to review.

On October 16 and 17, Phantom merged first-run fixes, renamed Verse to Phantom in user-facing text, sped up the app, and added a one-gateway guide.

On October 16 and 17, Ashlr Stack added one-command agent setup, Ashlr MD hardened its agent server, and the plugin re-measured its grep savings.

On October 16 and 17, Locus and Lexicon merged dozens of fixes found by driving them like an agent would, plus Gemini CLI support in Locus.

Jessica Wachtel’s single-run comparison found similar results on two agent tasks, with Muse Wonder using more tokens and costing more than Claude Fable 5.1.

A task in Claude Code, a review in Codex. Phantom brings coding agents into one workbench, with a place to steer the work and review what changed.

Speech-to-text gets common words right and your names wrong. Lexicon is one file of the words you say, fixed before your agent reads them.

Four bots give our CEO a manageable view of the work. Behind them are specialist agents, clear responsibilities and decisions that still stop with a person.

Which agent is working, and what needs approval? Phantom is our workbench; coordination for proactive agents is still being built.

Phantom 3.29.14 adds opt-in sleep prevention on Mac, a Devin dashboard reading that expires in two minutes, and a small coffee animation for Ash.