..as if we're operating this machine as analog synth
The consumer-facing chatbot interfaces just hide all that because they're aiming for a non-technical audience.
Also 14 string scans seems a little inefficient!
/thinking-tokens 32k
Or, shorthand: /think 32kSurely Anthropic could do a better job implementing dynamic thinking token budgets.
This fits my memory of it:
https://www.voicy.network/sounds/o_2r357a-kKEe5PaiWyYnA-quak...
Was it quake 2?
Similarly, I do miss an —add command line flag to manual specify the context (files) during the session. Right now I pretty much end up copy pasting the relative paths from VSCode and supply to Claude. Aider has much better semantics for such stuff.
You can use English or —add if you want to tell Claude to reference them.
BTW, as I was using it today, I was quite surprised to see `@` working now. Turns out in 0.27.5 they added this feature: https://github.com/anthropics/claude-code/blob/main/CHANGELO... :)
https://www.paritybits.me/think-toggles-are-dumb/
https://nilock.github.io/autothink/
LLMs with broad contextual capabilities shouldn't need to be guided in this manor. Claude can tell a trivial task from a complex one just as easily as I can, and should self-adjust, up to thresholds of compute spending, etc.
I mean finding your way around a manor can be hard, it's easier in an apartment.
> We recommend using the word "think" to trigger extended thinking mode, which gives Claude additional computation time to evaluate alternatives more thoroughly. These specific phrases are mapped directly to increasing levels of thinking budget in the system: "think" < "think hard" < "think harder" < "ultrathink." Each level allocates progressively more thinking budget for Claude to use.
I had a poke around and it's not a feature of the Claude model, it's specific to Claude Code. There's a "megathink" option too - it uses code that looks like this:
Notes on how I found that here: https://simonwillison.net/2025/Apr/19/claude-code-best-pract...