This is what most people in canada think of PP https://www.youtube.com/watch?v=Ysqevg-jbAA
Always thought it was "new" but made to sound like "boob" because it's funny.
Writing is thinking
Not until the anti-cheat situation is figured out. But I play most single player games on Linux these days.
I don't think it's clear at all.
Liam's Razor: Never attribute to misalignment what can be explained by a human seeking attention.
How is this better than using MCP?
Not sure why you're getting downvoted. This approach has been shown to work. The money isn't for funding the maintenance though, it's strictly to keep the riff-raff out.
I think you're projecting
This is exactly what I do. I don't get why everyone is trying to reinvent the whole development workflow/lifecycle. Our existing tools and processes are pretty good.
So when an agent does "cat file.txt" that's RAG to you?
The design I've landed over the years is to use both. The cookie is a session token and that's where you handle refresh tokens. Then there's an endpoint where you can mint a short-lived tenant-sepecific JWT. This holds…
I have a couple MCP servers connected to my Claude web & mobile clients. How would your clis work there?
Update the symlink to point at the previous version: ln -s $HOME/.local/share/claude/versions/2.1.153 $HOME/.local/bin/claude
JWTs are fine.
From my experience, it's the opposite. The more you fuck with them the more they call. It's better not to answer. But I just can't help myself.
The example with the dash in it confused me as well.
If you lost access to AI would you be able to continue development on your app?
My work involves fixing/adding stuff in legacy systems. Most of the solutions AI comes up with are horrible. I've reverted back to putting problems on my whiteboard and just letting it percolate. I still let AI write…
I get a kick out of publishing libs with no external deps. Regardless of reasoning, this change makes that easier.
This is exactly what I do. I assume most people avoid this approach due to cost.
Try ast-grep
This has been happening before LLMs too.
You don't need to retrain the whole thing from scratch every time.
LSP supports refactoring commands
This is what most people in canada think of PP https://www.youtube.com/watch?v=Ysqevg-jbAA
Always thought it was "new" but made to sound like "boob" because it's funny.
Writing is thinking
Not until the anti-cheat situation is figured out. But I play most single player games on Linux these days.
I don't think it's clear at all.
Liam's Razor: Never attribute to misalignment what can be explained by a human seeking attention.
How is this better than using MCP?
Not sure why you're getting downvoted. This approach has been shown to work. The money isn't for funding the maintenance though, it's strictly to keep the riff-raff out.
I think you're projecting
This is exactly what I do. I don't get why everyone is trying to reinvent the whole development workflow/lifecycle. Our existing tools and processes are pretty good.
So when an agent does "cat file.txt" that's RAG to you?
The design I've landed over the years is to use both. The cookie is a session token and that's where you handle refresh tokens. Then there's an endpoint where you can mint a short-lived tenant-sepecific JWT. This holds…
I have a couple MCP servers connected to my Claude web & mobile clients. How would your clis work there?
Update the symlink to point at the previous version: ln -s $HOME/.local/share/claude/versions/2.1.153 $HOME/.local/bin/claude
JWTs are fine.
From my experience, it's the opposite. The more you fuck with them the more they call. It's better not to answer. But I just can't help myself.
The example with the dash in it confused me as well.
If you lost access to AI would you be able to continue development on your app?
My work involves fixing/adding stuff in legacy systems. Most of the solutions AI comes up with are horrible. I've reverted back to putting problems on my whiteboard and just letting it percolate. I still let AI write…
I get a kick out of publishing libs with no external deps. Regardless of reasoning, this change makes that easier.
This is exactly what I do. I assume most people avoid this approach due to cost.
Try ast-grep
This has been happening before LLMs too.
You don't need to retrain the whole thing from scratch every time.
LSP supports refactoring commands