News for hackers. Stuff that matters.
Re:I Cancelled Claude: Token Issues, Declining Quality, and ... by onlyrealcuzzo on Friday April 24, 2026 @04:00PM (#47895084)
> My anecdata is that it heavily depends on how much of the relevant code and instructions it can fit in the context window.

Agreed, but I'm working on something >100k lines of code total (a new language and a runtime).

It helps when you can implement new things as if they're green-field-ish AND THEN implement and plumb them later.

Re:I Cancelled Claude: Token Issues, Declining Quality, and ... by antonvs on Saturday April 25, 2026 @01:11AM (#47898821)
In a well-designed system, you can point an agent at a module of that system and it's perfectly capable of dealing with it. Humans also have a limited context window, and divide and conquer is always how we've dealt with it. The same approach works for agents.
Re:I Cancelled Claude: Token Issues, Declining Quality, and ... by onlyrealcuzzo on Monday April 27, 2026 @02:38PM (#47925472)
> In a well-designed system, you can point an agent at a module of that system and it's perfectly capable of dealing with it.

Yes, but the problem is that LLMs don't default to well-designed systems... So, you need to aggressively stay on top of them.