That makes resuming easier, if you remember to rename in your current session. But that doesn’t solve being able to search history from earlier in your current session or from your entire history of sessions. Or resuming sessions for which you’ve forgotten the name.
Nice! Tangentially related: I built a (MacOS only) tool called clippy to be a much better pbcopy. It was just added to homebrew core. Among other things, it auto-detects when you want files as references so they paste into GUI apps as uploads, not bytes.
clippy image.png # then paste into Slack, etc. as upload
clippy -r # copy most recent download
pasty # copy file in Finder, then paste actual file here
Adding the word "then" to your first comment would have helped me: (lacking context, I thought the comments explained what the command does, as is common convention)
clippy image.png # then paste into Slack, etc. as upload
Also:
pasty # paste actual file, after copying file in Finder
Interesting - this is the exact problem José Valim cited when creating Elixir: he was working on Rails multi-core performance in 2010 and found that "writing multi-core software, which is software that runs on all cores with Ruby, was not really straightforward."[1] Ruby's GIL meant only one thread executes at a time.
Fleury's arriving at similar conclusions from the C/systems side: make multi-core the default, not an opt-in. Though his approach still requires explicit coordination (LaneIdx(), barriers, range distribution) vs BEAM where the scheduler automatically distributes processes across cores.
Different tradeoffs for different domains, but both are reacting to the same backwards reality where we program single-core-first on multi-core hardware.
> Though his approach still requires explicit coordination (LaneIdx(), barriers, range distribution) vs BEAM where the scheduler automatically distributes processes across cores.
I don't see how a separate and abstract scheduler handing out tasks is any faster/better.
Being explicit isn't always a bad thing. It lets you better understand and control what is going on, which is very useful.
For example: in one of the examples Fleury gave in the aticle, he showed how you could take advantage of this explicitness to avoid having to wait on other threads just to get a new task to work on. (https://www.rfleury.com/i/172146732/dynamically-assigning-ma...)
Inspired by the copy-paste point in this post, I added agent buffer tools to clippy, a macOS utility I maintain which includes an MCP server that interacts with the system clipboard. In this case it was more appropriate to use a private buffer instead. With the tools I just added, the server reads file bytes directly - your agent never generates the copied content as tokens. Three operations:
buffer_copy: Copy specific line ranges from files to agent's private buffer
buffer_paste: Insert/append/replace those exact bytes in target files
buffer_list: See what's currently buffered
So the agent can say "copying lines 50-75 from auth.py" and the MCP server handles the actual file I/O. No token generation, no hallucination, byte-for-byte accurate. Doesn't touch your system clipboard either.
The MCP server already included tools to copy AI-generated content to your system clipboard - useful for "write a Python script and copy it" workflows.
(Clippy's main / original purpose is improving on macOS pbcopy - it copies file references instead of just file contents, so you can paste actual files into Slack/email/etc from the terminal.)
Don't know why this is getting downvoted. Agree with this so hard, as a continually aggrieved Fly customer (close to becoming an ex-customer). The too cool for school schtick gets old fast when they don't have the goods to back it up.
I tried Terragon on an open source repo I maintain and ended up with a PR: "Showing 11,643 changed files with 2,441,792 additions and 584 deletions." Yikes!
Thanks. I just released a new version with UTI based MIME type detection as the primary method with a fallback to the existing content-based detection.
clippy is a bit different from these - rather than requiring manual flags for MIME types, it automatically detects the content type. The idea is to make the CLI's copy/paste feel as intuitive as the GUI's.
I might tackle Linux (and Windows) at some point, but contributions are definitely welcome!
reply