Hacker News new | past | comments | ask | show | jobs | submit login

The "ultrathink" thing is pretty funny:

> 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:

  let B = W.message.content.toLowerCase();
  if (
    B.includes("think harder") ||
    B.includes("think intensely") ||
    B.includes("think longer") ||
    B.includes("think really hard") ||
    B.includes("think super hard") ||
    B.includes("think very hard") ||
    B.includes("ultrathink")
  )
    return (
      l1("tengu_thinking", { tokenCount: 31999, messageId: Z, provider: G }),
      31999
    );
  if (
    B.includes("think about it") ||
    B.includes("think a lot") ||
    B.includes("think deeply") ||
    B.includes("think hard") ||
    B.includes("think more") ||
    B.includes("megathink")
  )
    return (
      l1("tengu_thinking", { tokenCount: 1e4, messageId: Z, provider: G }), 1e4
    );
Notes on how I found that here: https://simonwillison.net/2025/Apr/19/claude-code-best-pract...





Not gonna lie: the "ultrathink" keyword that Sonnet 3.7 with thinking tokens watches for gives me "doubleplusgood" vibes in a hilarious but horrifying way.

At this point should we get our first knob/slider on a language model... THINK

..as if we're operating this machine as analog synth


There are already many such adjustable parameters such as temperature and top_k

That's awesome, and almost certainly an Unreal Tournament reference (when you chain enough kills in short time it moves through a progression that includes "megakill" and "ultrakill").

If they did, they left out the best one: "m-m-m-m-monsterkill"

Surely Anthropic could do a better job implementing dynamic thinking token budgets.


Ultrakill is from Quake :)

In aider, instead of “ultrathink” you would say:

  /thinking-tokens 32k
Or, shorthand:

  /think 32k

What I don’t like about Claude Code is why can’t they give command line flags for this stuff? It’s better documented and people don’t have to discover this the hard way.

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.


Weird code to have in a modern AI system!

Also 14 string scans seems a little inefficient!


14 checks through a string is entirely negligible relative to the amount of compute happening. Like a drop of water in the ocean.



Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: