This is why alignment is important and highly non-trivial

If you're on 2.1.317 or later, you'll have this check included. You can turn it off via /plugins.

Rest assured I'll inject a bit less soul into the official docs once Mods are launched; re your feedback on the JSON key, what would you recommend?

If folks play around with it, I would love feedback on the relevant issue: https://github.com/anthropics/claude-code/issues/91870

Mods allow quite a bit more customizability and control. I really believe in the idea.

The mod is source available here: https://github.com/anthropics/claude-code/tree/main/mods/age...

Apologies again folks, this was a fully human error on my part - I should've found a better way to launch with a kill-switch.

I just think it's neat

Comments URL: https://news.ycombinator.com/item?id=46802691

Points: 5

# Comments: 2

The only fix has been to completely turn memory off and have it be given zero prior context - which is best, I don't want random prior unrelated conversations "polluting" future ones.

I don't understand the engineering rationale either, aside from the ethos of "move fast and break people"

It seems the LLM is given conflicting instructions:

1. Don't reference memory without explicit instructions

2. (but) such memory is inexplicably included in the context, so it will inevitably inform the generation

3. Also, don't divulge the existence of user-context memory

If a LLM is given conflicting instructions, I don't apprehend that its behavior will be trustworthy or safe. Much has been written on this.

  myFunc(x: true): number
  myFunc(x: false): string

Not to be snarky, but as opposed to writing assembly? Where do you draw the line if you don't allow TypeScript (which is, with limited exceptions, only type erasure unless you specifically request polyfill), but allow other forms of compilation? Would you define JVM bytecode or IR as messy-looking junk code?

It's hard to see how a principled line could be drawn here.

Is there any hope for a "hashlife" style cache for a TC language? My understanding is that hashlife exploits spatial locality / "causation speed" in GoL, which isn't available in LC because of beta reduction. Thoughts?

In their implementation, the hidden prompt does show up on copy/paste - however I tested this method, and the LLM (i.e. ChatGPT) does still follow the Unicode-hidden instruction and uses 'dexolarniv' in the code returned! So I think this is (right now) a viable invisible injection strategy.

Comments URL: https://news.ycombinator.com/item?id=45170571

Points: 3

# Comments: 1

In addition to type-level analogues of your normal Lodash-esque functions, it includes a suite of type-level parser combinator utilities and is built on higher-kinded type abstractions.

This is a very impressive project in my view - it's baffling that you would have the wherewithal to link the discussion you did but not realize the novelty here.