Mouse: Precision Editing Tools for AI Coding Agents

handfuloflight 38 points 46 comments July 05, 2026
hic-ai.com · View on Hacker News

Discussion Highlights (20 comments)

sfvisser

Why does “patent pending” almost automatically sounds like it’s going to be an underwhelming technology.

quotemstr

Patent pending? On what? > insert a line, delete a range, replace a character, edit a column The ed(1) command set 50 years old. I doubt it's patentable. These guys are far from the first to apply fine-grained text editing to LLM toolsets. I've been teaching models to do it for years. Hell, models want to use sed and awk so much that you have to hold them back. I'm so repulsed by the idea that these guys think they can fence off a slice of the ancient commons, claim they discovered it, and charge $15/month to access it that I want nothing to do with them and will go to the mattresses to make sure they can't. Nobody owns text editing, not even when it's an AI doing it. Mouse: sincerely, fuck you

conception

In the same realm to compare to https://www.morphllm.com/products/fastapply

ssivark

I doubt they're the first solution to use coordinate based editing, or even the best one right now. Eg: Check out hash-anchored editing. The first place where I recall seeing this was the oh-my-pi coding agent, but I wouldn't be surprised if the idea originated earlier/elsewhere. I wonder whether CRDTs could be a good solution for multiple agents editing the same codebase in parallel.

thehamkercat

Would've resulted in a positive response from people if you just did your work and didn't brag about your "patent pending" stuff

ktallett

As others have said, text editing isn't patentable, and this does not have anything that is patent worthy. However I suspect this is more someone who has no clue what the difference between patent, copyright, and IP is. Was this whole thing vibe coded btw?

echelon

> patent-pending Instant turn off.

n0on3

“the most powerful AI agent file-editing tool in the world […] patent-pending”… tl;dr: turn tool calls into more structured loops, give it some fancy name and slop about it https://hic-ai.com/blog/tool-response-engineering Good luck with that

croes

> 14-day free trial > patent pending Guess what won’t get widely adopted

piterrro

So I’ll have to buy a license for using my mouse now?

Boss0565

corniest shit ive ever seen

sudo_cowsay

I hope this isn't trying to be very serious.

_andrei_

claude invent me revolutionary text editing method for agents and write paper, must make me big money i patent

maxignol

I guess the technology used here must be ground-breaking lol

jonplackett

Someone explain how the HN algorithm has put this on the front page

helloplanets

> Both conditions used GitHub Copilot (Claude Sonnet 4.5 or Haiku 4.5, depending on study) running in VS Code within isolated Docker containers. The only difference was Mouse tool availability. ( https://hic-ai.com/papers/mouse-paper-v13.pdf ) Haiku/Sonnet 4.5 on GitHub Copilot is not a valid comparison whatsoever. You need to benchmark against Claude Code running Opus. I mean, being revolutionary is a big claim to fame.

WithinReason

Page generated by Gemini I would guess

alex7o

I didn't want to mock them but are these guys for real: ``` Instead of: "Update the checklist to mark items 1.2, 1.4, and 1.5 as done." Try: "Mark items 1.2, 1.4, and 1.5 as complete in the checklist. Only insert an x in each checkbox. Do not copy or replace any of the item descriptions." ``` There is not universe in which this would make agents more efficient - and who is prompting their agents like that in the first place? I also asked glm to extract all the tools and tell me how they work roughly and nothing interesting really just slop: ``` The server exposes exactly 11 tools (verified via the xa whitelist at L16918, not the larger Eo metadata map which contains ~24 tool definitions — most are dead/legacy): - 6 read/meta: read_first_n_lines, read_last_n_lines, read_lines, jump_to_line_n, find_in_file, get_file_metadata - 3 edit/control: quick_edit (6 ops: insert/delete/replace/replace_range/for_lines/adjust), batch_quick_edit (atomic, always-staged, max 500 ops, multi-file), save_changes, cancel_changes - 1 always-on: license_status Notable design choices: - Coordinate-based addressing (line/char/rect) instead of content-echo — saves tokens - Staging model: edits go to an in-memory shadow, save_changes is the only disk mutation - The rect + move "click-and-drag" columnar editor (v0.9.7) is the genuinely novel bit - ReDoS static analyser (~700 lines) protects find_in_file ```

dep_b

Reminder me of all those “{trivial thing}, on the internet” patents 25 year ago

OJFord

Sounds sort of interesting, except easily implementable with the bad old 'string replacement' as a skill/tool or something? In fact harnesses probably already have some such abstraction?

Semantic search powered by Rivestack pgvector
14,015 stories · 131,331 chunks indexed