I had a similar experience earlier this year. Cheaper situation than a mainframe, but... why do some companies make it hard for them to take my money? I'm already a customer ffs.
I'm stuck on Windows, so oh-my-pi has been really nice. The others I've tried such as kilo do alright but tool calling can mess up a bit.
Only complaint is that connecting the agent harness to my local model took more work getting configured right than I'd like, but that's been true of most harnesses I've tried as well. Most assume you're using a cloud model and local model configuration is a bit of an afterthought.
I tried many of these pi extensions but they have tons of paper cuts. Don't remember which one had which issue but here are some I ran into:
* commands run by me (! prefix) are also sandbox blocked
* agent has no way to _request_ unsandboxed execution (e.g. if `kubectl whatever` is rejected by the sandbox, the model should have the chance to request permission)
* does not understand shell composition patterns (e.g. if `git status` is allowed and `git log` is allowed, then `git status && git log` should be allowed automatically)
* sandbox only supported on mac or linux. not both
All of that can be fixed by yourself. That's certainly the spirit of pi. But if you want strong defaults and batteries included (like omp promises) then that's just annoying.
- instruct model to write a markdown file with a phased plan to implement whatever feature or change I want
- start a new context, instruct model to implement one phase of the file
- review changes manually, then start a new context and have it do the next phase
- repeat as needed
I've never seen omp touch a file outside of the directory I start it up in, and the few times where I've been unhappy with a change git has been there to revert.
This could easily be a case of survivor bias but I've not had an issue with letting it go yolo yet.
Sometimes agents create huge half-minified one-off python/bash scripts to do some data processing. I'd prefer to neither review nor yolo these. Sandbox restricts reads/writes to designated directories, so at least there's no `rm -rf /` in there.
Well, it is an indication that it matters to the lab, so if you don't want legal fees to be the first one to set precedent, then it does matter a great deal.
You could say the same thing about "license-washing" the model. It seems like you're just going through a guaranteed expensive process to have roughly the same risk as just using the model and potentially getting hit with legal fees.
It comes up frequently when discussing whether LLMs actually have intelligence or qualify as AI, especially in discussions on the path to achieving AGI.
The primary complaint seems to be that LLMs are held to a higher standard than humans, though I don't particularly buy that line of reasoning.
Break it into small chunks and practice. Practice more. Put the chunks together and practice even more. Like any skill, it isn't something people are magically good at beyond minor proficiency.
Every performance- singing a song, playing an instrument, performing a stand-up routine, giving a speech, performing a theatrical role are all things that are best done from memory but require practice.
There are pneumonic tricks you can use- I've seen some people do it for tricks like memorizing the order of a deck of cards- but it's less useful for long term recital because it helps with order but not comprehension or fast indexing.
You aren't arguing for jailbreaks, you are arguing for the phone to be in the user's full control.
Ideally, ios and Android would be secure enough that no jailbreaks are possible, but open enough to allow the user to replace the OS with one of their choosing.
Having it locked down and then resorting to exploiting loopholes is the worst of both worlds.
I wonder if we would have been capable of endurance hunting without both lungs. I suspect that changing that would have very drastically changed human development.
reply