AnyBot

Author	SHA1	Message	Date
王性驊	3d10499d55	GTK 2 apps in the box get numbers, a quick model's answer always goes past the bot's own model, and a bot finishes what it was asked - Box v9: GTK_MODULES=gail:atk-bridge. lxappearance and PCManFM (GTK 2) offered AT-SPI no controls at all (0 numbers); with gail they offer 37 and 17. - The quick model ending a turn without acting goes to the bot's own model every time, not only after changes: one stopped after a single look to ask 「要我繼續嗎？」. - Instructions: finish what was asked; put an unexpected screen right (close what's in the way, open the app) instead of stopping to ask, except for what the person must do or confirm. - Benchmark: three more held-out tasks (lxappearance theme, PCManFM folder, Mousepad find-and-replace), checked by their results; every task starts with those apps closed too. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Uirha5F5gJt93t3yEx3XcS	2026-11-09 12:53:06 +08:00
王性驊	be790f36ba	Screen steps name their controls first, and a batch takes a whole row of keys; four held-out tasks A quick model looking numbers up pressed 1, 2, 3, 1 for 1234, and 1234 × 5678 = didn't fit in an 8-action batch (it split it and lost a key). The click and batch descriptions now lead with the control's name (name "4"), and a batch takes up to 16 actions. The benchmark gets four tasks on things none of the others use (Mousepad and its save dialog, a Chromium bookmark, ImageMagick, a page of nested web components), run only when asked for (--tasks N1,…): a check that the changes carry over to what they weren't tuned on. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Uirha5F5gJt93t3yEx3XcS	2026-11-09 09:36:50 +08:00
王性驊	bcae66b21a	A computer-use benchmark: eight fixed tasks on a throwaway box, timed step by step bench/computer-use/run.py runs each task through `anybot --ask` with a fresh chat, checks the result inside the box, and records success, steps, time split between model and tools, route switches and a per-step transcript. It refuses to run against the real box (needs its own ANYBOT_BOX_NAME / ANYBOT_BOX_VOLUME and a scratch data folder). --keep-skills carries learned skills into the next run to measure replay. README has the tasks, how to run, and the 2026-11-09 numbers. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Uirha5F5gJt93t3yEx3XcS	2026-11-09 09:00:48 +08:00

Author

SHA1

Message

Date

王性驊

3d10499d55

GTK 2 apps in the box get numbers, a quick model's answer always goes past the bot's own model, and a bot finishes what it was asked

- Box v9: GTK_MODULES=gail:atk-bridge. lxappearance and PCManFM (GTK 2) offered AT-SPI no
  controls at all (0 numbers); with gail they offer 37 and 17.
- The quick model ending a turn without acting goes to the bot's own model every time, not only
  after changes: one stopped after a single look to ask 「要我繼續嗎？」.
- Instructions: finish what was asked; put an unexpected screen right (close what's in the way,
  open the app) instead of stopping to ask, except for what the person must do or confirm.
- Benchmark: three more held-out tasks (lxappearance theme, PCManFM folder, Mousepad
  find-and-replace), checked by their results; every task starts with those apps closed too.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha5F5gJt93t3yEx3XcS

2026-11-09 12:53:06 +08:00

王性驊

be790f36ba

Screen steps name their controls first, and a batch takes a whole row of keys; four held-out tasks

A quick model looking numbers up pressed 1, 2, 3, 1 for 1234, and 1234 × 5678 = didn't fit in
an 8-action batch (it split it and lost a key). The click and batch descriptions now lead with
the control's name (name "4"), and a batch takes up to 16 actions.

The benchmark gets four tasks on things none of the others use (Mousepad and its save dialog,
a Chromium bookmark, ImageMagick, a page of nested web components), run only when asked for
(--tasks N1,…): a check that the changes carry over to what they weren't tuned on.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha5F5gJt93t3yEx3XcS

2026-11-09 09:36:50 +08:00

王性驊

bcae66b21a

A computer-use benchmark: eight fixed tasks on a throwaway box, timed step by step

bench/computer-use/run.py runs each task through `anybot --ask` with a fresh chat, checks the
result inside the box, and records success, steps, time split between model and tools, route
switches and a per-step transcript. It refuses to run against the real box (needs its own
ANYBOT_BOX_NAME / ANYBOT_BOX_VOLUME and a scratch data folder). --keep-skills carries learned
skills into the next run to measure replay. README has the tasks, how to run, and the
2026-11-09 numbers.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha5F5gJt93t3yEx3XcS

2026-11-09 09:00:48 +08:00

3 Commits