I don't know enough about the US legal system to comment but there certainly does sometimes seem to be an element of "whoever has the most money to throw at lawyers wins".
It's not hard to imagine how a person who suffered legitimate abuse at the hands of one of the most influential people on earth could develop this kind of paranoia.
It's only slightly harder to imagine that the tech oligarchy really is conspiring against her.
So, if you were accused of raping someone, you should just suck it up and go to jail and just because you have money, you are guilty, right? Not supporting Sam here, but this kind of thinking sets a dangerous precedent.
It just means what they said, that if you're a billionaire, getting a case thrown out in a country like the USA, shouldn't get you any points regarding to common people's belief if you're guilty or not.
That's just how it is. In the US he gets to not go to jail in a justice system where nobody believes he's actually innocent, because he has money.
If you believe the hype then this isn't a transformation like, say, the power loom replacing handmade textiles. Both AI boosters and doomers are envisioning a future where almost all white collar work is obsolete. It isn't just one industry, its broad swaths labour across all segments of the economy.
LSPs don't really do this. They're like a better way to grep for something (so they do address the previous thing I said about listing all function names etc.) But they often don't say (depending on the particular LSP setup etc) this function ends at this char and they definitely don't then provide the text editing tool
This is not accurate. Most LSPs do provide text editing tools, which the Language Server Protocol calls "code actions". These actions do things like: reorganizing imports, expanding macros, extracting a selection into a function, or converting one type of control flow into another (e.g. if to match). Common LSPs, like rust-analyzer and Ruff (Python) support code actions. Editors also expose code actions: Zed, for instance, exposes actions under the default keymap with the binding Command + .
Come on what are we talking about. Ruff is a linter. Can you show me any LSP server that can move an arbitrary function from file1.ts to file2.ts based on calling it on the command line?
They're not command line applications, they use JSON-RPC inline, and it's an interactive flow, so you need the client to actually persist state.
So what you'd see in the LLM traces, for example, is a couple back-and-forths using JSON-RPC. It absolutely works at the moment, and claude code will happily use it if everything is set up correctly, just tested it using https://github.com/typescript-language-server/typescript-lan...
I was just using it as an example of how dropping claude / gpt in a Linux shell and saying good luck and then giving interviews about spawning sub agents seems to overlook basic text editing primitives
But if you managed to move an arbitrary char range from one file to another using Claude Code talking to the TS LSP server let me know that would be enlightening.
The relevant points have already been made: (1) LSP is a JSON-RPC protocol, not a CLI app, and (2) Language Servers that implement LSP often utilize AST manipulation, even the resultant manipulations are exposed to the client via character ranges.
`ast-grep`, an AST-based search and transformation tool that may be closer in spirit to the cli functionality you describe, albeit more general-purpose:
https://github.com/ast-grep/ast-grep
Interesting. But I think this also proves my point that if this particular LSP server has the move statements functionality the pattern is not default integrated into Claude Code, OpenAI Codex, etc. Like you’d have to figure out a way to keep this server running yourself as if you were running Redis and asking the harness to manage your ToDos in it or something
Jesus christ dude, what you're describing is what an LSP is. It is a server that runs, and integrates with editors, and claude code uses the LSP the same way an editor does. It does, in fact, stay running in the background along side claude code as an independent process. There's no "gotcha" here.
Again this is exactly equivalent to saying Claude Code doesn’t need a todo tool (which it has ie TaskList) cause you can run Redis. What you have demonstrated is that there is a lengthy workaround depending on if a particular LSP server implements a move method .. to do text editing
No, not an arbitrary character range, it's quite a lot smarter than that. It's an AST transformation - it takes the parsed tree out and puts it in another file and updates any imports that refer to the prior function to the new location. That all happens in the LSP side, not the LLM side, so it's deterministic. You can look at the source code for the LSP yourself.
You're basically just agreeing with the original comment that these tools don't do what's stated.
And in my experience, Claude Code will often ignore LSPs, despite instructing Claude to use them and have them installed through Claude, and revert to using grep and sed.
it does look to have a method for moving a function to a new file
I give my agent access to go pls and find it overall beneficial, based on vibes eval. Its way easier to ask LSP everywhere a function or field is used versus grep, saves a lot of tokens
I've had decent results telling agents to use emacs for structural editing operations. Pretty rare that I need to move a function across files verbatim but that should only be a few extra lines of elisp.
A billionaire managing to get a case dismissed in the US legal system hardly suggests an accusation has no merit.
reply