unfortunately all the agent cli makers have decided that simply giving it access to bash is not enough. instead we need to jam every possible functionality we can imagine into a javascript “TUI”.
If all you want is a program that calls the model in a loop and offers a bash tool, then ask Claude Code to build that. You won't like it though!
For a preview of what it'd be like, just tell your AI chat app that you'll run bash commands for it, and please change the app in your "current directory" to "sort the output before printing it", or some such request.
Claude Code with Opus 4.6 regularly uses sed for multi-line edits, in my experience. On top of it, Pi is famously only exposing 4 tools, which is not just Bash, but far more constrained than CCs 57 or so tools.
I think the problem/limitation would be as much due to context management as tools. Obviously bash plus a few utilities is sufficient to explore/edit the code base, but I can't imagine this working reliably without the models being specifically trained to use specific tools, and recognize/adapt to different versions of them etc.
Context management, both within and across sessions, seems the bigger issue. Without the agent supporting this, you are at the mercy of the model compacting/purging the context as needed, in some generic fashion, as well as being smart enough to decide to create notes for itself tracking what it is doing, etc.
Apparently CC is 512K LOC, which seems massively bloated, but I do think that things like tools, skills, context management and subagents are all needed to effectively manage context and avoid the issues that might be anticipated by just telling the model it's got a bash tool, and go figure.
I thought CC only supports it's find/replace edit tool (implemented by CC itself, using Node.js for file access), and is platform agnostic. Are you saying that on linux CC offers "sed" as a tool too? I can't imagine it offers "bash" since that's way too dangerous.
Yes, Claude Code has a Bash tool, and Claude in some cases uses the CLI sed utility (via the Bash tool) for file changes (although it has built-in file update), at least on my Linux machine.
I just asked Claude, and apparently CC makes it's bash tool available on all platforms it runs on (Linux, macOS, Windows WSL, Git for Windows), and doesn't do platform-specifc filtering of bash commands, which would seem to make for some interesting incompatibilities - GNU utils (sed, grep, find) on Linux and Windows, but BSD variants on macOS.
> If all you want is a program that calls the model in a loop and offers a bash tool, then ask Claude Code to build that. You won't like it though!
Okay sure it’s technically more than just bash, but my own for-fun coding agent and pi-coding-agent work this way. The latter is quite useful. You can get surprisingly far with it.
i did.. and thats what i use. obviously its a little more than just a tool that calls bash but it is considerably less than whatever they are doing in coding agents now.
Agreed. I came in the comments to say something similar. I think the author raises some interesting points worth consideration but their perspective is so incredibly cynical. He mentioned a small team that made the Apollo computer program. Well it took an awful lot more than a computer program to get to the moon. I don’t think anybody would argue that there are people who don’t pull their weight out there but there is so much evidence that people working together actually works that it makes you wonder who hurt the author so much.
I fail to grasp the basis of folks knee-jerk dismissal of just about anything that strikes them as "cynical". Like, what world do you live in that cynicism isn't a signal of clear vision?
There's also a lot of evidence it doesn't work. It's not either/or.
This piece is more of a whine about a certain kind of office culture, which the author - unreasonably - generalises to collaboration as a whole.
There's likely a lot of money to be made by identifying and defining good vs bad collaborative cultures.
Both are real. But a lot of "good" practices are more cargo culty than genuinely productive, and the managers who really do make it work seem to get there more by talent and innate skill than learned effort.
The layoffs are not necessarily executed in a way that takes performance into account, but that doesn’t mean that the industry overall doesn’t have too many people for the amount of work that needs to be done.
Its only the part about casting any aspersions at the people laid off for being low performance that bothers me because I know so many incredible people for whom they absolutely did not deserve it and its not fair to assume anything about their value or quality of their work specifically.
> that doesn’t mean that the industry overall doesn’t have too many people for the amount of work that needs to be done.
Not that I disagree with you here, but it is hard to square this with people who are also saying not to worry about AI displacement because there's limitless demand for software.
Depends on the industry and product, as usual. On an large level, I do not think there's "too many engineers and not enough problems to be solved". Companies are simply hunkering down for a recession we can't say out loud.
The ammount of shrinkflation in the last year is just stunning. Sometimes they bother to make the bottle/box/can incrementally imperceptibly smaller. Sometimes they just put less in. I track macros so I'm always looking at weights, and they're generically down 20%, while prices are up.
They ALSO know that and are making a stand about this in particular use of figurative language since anthropomorphizing llms is a thing we're already seeing used for accountability washing. If we, the public, don't let the language shift to acting like these LLMs are actual people then we, the public, can do a better job of keeping our intuitions right about who is responsible for these products doing wacky/destructive/abusive/evil things instead of falling into the trap of "<personified name of LLM product > did/said it".
No that’s not true at all. Humans can deal with ambiguity and operate independently. Claude can’t do that. You’re trading one “problem” for an entirely different one in this hypothetical.
Because nobody actually wants to talk about the core of the problem or how to address it. They see different, seemingly unrelated problems depending on what their priorities are. The democrats are also not on the side of actually solving the problem.
