“Amp replaced named agent modes with a four-position capability dial — low, medium, high, ultra — switchable with Ctrl+S or the web picker, and wired to specific model + reasoning-effort stacks: ultra = Claude Fable 5 (writer) with GPT-5.6 Sol as oracle; high = GPT-5.6 Sol at xhigh with Claude Fable 5 as oracle; medium = GPT-5.6 Sol at medium (with a high-effort Sol oracle); low = GLM-5.2 (admins may opt for GPT-5.6 Terra low) with GPT-5.6 Sol as oracle.”

The Chronicle item explains how Amp maps different models and reasoning levels to a single capability dial.

“Amp now lets you start new agents remotely from anywhere you can run amp; enable remote thread creation with the command amp: enable remote creation of threads or by setting amp.remoteThreadCreation.enabled to true in ~/.config/amp/settings.json, after which every Amp client will accept and run new threads in its working directory.”

Ampcode Chronicle Agents, Anywhere - Amp now lets you start new agents remotely from anywhere you can run amp; enable remote thread creation with the command amp: enable remote creation of threads or by setting amp.remoteThreadCreation.enabled to true in ~/.config/amp/settings.json, after which every Amp client will accept and run new threads in its working directory. Use runner mode with amp --no-tui to run headless runners that only wait to start and run new threads; you can run multiple runners on the same machine if started in different directories, each runner identified by host and working directory, and directories need not be version controlled.

“Amp now offers four orb sizes: a0.tiny (1 CPU, 2GB memory, 40GB disk, $0.10/hour), a0.small (2 CPUs, 4GB, 40GB, $0.21/hour), a0.medium (8 CPUs, 16GB, 40GB, $0.83/hour) and a0.large (16 CPUs, 32GB, 40GB, $1.66/hour) which is the default; orb storage has been doubled from 20GB to 40GB at no extra cost and you can change a project's orb size in Project Settings.”

#8 📝 Ampcode Chronicle More Orb Sizes - Amp now offers four orb sizes: a0.tiny (1 CPU, 2GB memory, 40GB disk, $0.10/hour), a0.small (2 CPUs, 4GB, 40GB, $0.21/hour), a0.medium (8 CPUs, 16GB, 40GB, $0.83/hour) and a0.large (16 CPUs, 32GB, 40GB, $1.66/hour) which is the default; orb storage has been doubled from 20GB to 40GB at no extra cost and you can change a project's orb size in Project Settings.

“You can create custom agents in Amp via plugins and use them as main agents or subagents, include them in tool pipelines or spawn up to 25 worker agents, with each agent getting a custom orb color.”

#5 📝 Ampcode Chronicle Custom Agents - You can create custom agents in Amp via plugins and use them as main agents or subagents, include them in tool pipelines or spawn up to 25 worker agents, with each agent getting a custom orb color. The examples show amp.createAgent using model openai/gpt-5.5, registering a focused_review tool and an agent mode, and demonstrate thread APIs—createThread, appendUserMessage (returns immediately), waitForResponse—and an async start_async_review tool that spawns a background thread and returns Started background review in ${thread.id}.

“#16 📝 Ampcode Chronicle Diffs - Amp now lets you review any thread's code changes directly in Amp on desktop or mobile, scroll through diffs, request changes on specific sections, and interactively stage edits while a thread has an active environment.”

#16 📝 Ampcode Chronicle Diffs - Amp now lets you review any thread's code changes directly in Amp on desktop or mobile, scroll through diffs, request changes on specific sections, and interactively stage edits while a thread has an active environment. The diff algorithm detects duplicate blocks to highlight true changes (example: showing only the removed if-branch), and you can open the current thread's diff in your browser from the terminal via the command palette shortcut Ctrl‑O.

“Amp's deep and rush modes now deliver the first token 87% faster and p50 full responses 32% faster, mainly by switching to WebSockets for OpenAI communication and from a rebuild of Amp last month; on long-horizon tasks end-to-end speedups reach up to 40%.”

#20 📝 Ampcode Chronicle Faster Deep & Rush - Amp's deep and rush modes now deliver the first token 87% faster and p50 full responses 32% faster, mainly by switching to WebSockets for OpenAI communication and from a rebuild of Amp last month; on long-horizon tasks end-to-end speedups reach up to 40%.

“Opus 4.8 replaces Opus 4.7 in Amp's smart mode and solved 62% of tasks in Amp's internal evals (up from 52% for 4.7), running tests and code 15% more per task while making tighter, more focused edits.”

#14 📝 Ampcode Chronicle Opus 4.8 - Opus 4.8 replaces Opus 4.7 in Amp's smart mode and solved 62% of tasks in Amp's internal evals (up from 52% for 4.7), running tests and code 15% more per task while making tighter, more focused edits. It reaches for external tools more appropriately—calling librarian 14 times versus 1 for 4.7 and using edit_file for 79% of file edits (up from 63%)—drops the Read tool, and adds a ~2.5× fast mode that costs 2× base tokens (down from 6× on 4.7).

“#11 📝 Ampcode Chronicle GPT Image 2 Paints Better - Amp's painter tool now uses GPT Image 2, which Amp claims outperforms Gemini 3 Pro Image at preserving existing text, typography, and visual style when editing UI screenshots while costing roughly one-quarter the price.”

#11 📝 Ampcode Chronicle GPT Image 2 Paints Better - Amp's painter tool now uses GPT Image 2, which Amp claims outperforms Gemini 3 Pro Image at preserving existing text, typography, and visual style when editing UI screenshots while costing roughly one-quarter the price. In an example thread, Painter converted a screenshot of the Chronicle page into an updated design while retaining its original visual style.

“Amp released Rush 2.0, which now uses GPT-5.5 with no reasoning and is tuned for small, focused code edits using shell_command for search/read/verify and apply_patch for edits, with task subagents sharing the same config and several redundant tools removed.”

#18 📝 Ampcode Chronicle Rush, 2.0 - Amp released Rush 2.0, which now uses GPT-5.5 with no reasoning and is tuned for small, focused code edits using shell_command for search/read/verify and apply_patch for edits, with task subagents sharing the same config and several redundant tools removed.

“Claude Opus 4.7 is now powering Amp's smart mode, improving ability to solve harder problems.”

#4 📝 Ampcode Chronicle Opus 4.7 - Claude Opus 4.7 is now powering Amp's smart mode, improving ability to solve harder problems. However, it is less forgiving of vague prompts and may produce weaker results when prompts lack clarity. #5 𝕏 Google Research is demoing on-device Sensitive Content Warnings in Google Messages, an AI feature that filters unwanted content locally while keeping all processing private.