https://help.openai.com/en/articles/20001106-codex-rate-card https://help.openai.com/en/articles/11481834-chatgpt-rate-ca...

(I didn't think to include a UUID checker though - nice touch)

Thanks to the Claude Code source code leak I was able to reverse engineer how it all works. Due to their PRNG choice (Mulberry32) it's trivial to crack all 4.29 billion seeds in seconds.

Some findings:

- 1% legendary chance: 42,989,564 seeds out of 2^32 produce legendaries - Stats & shiny appear to be dead code: rolled but never read anywhere. Pure bragging rights? - Commons can't have hats, only uncommon+ rolls from the hat table - "God" rolls exist: legendary + shiny + a maxed stat at 100.

[1] https://news.ycombinator.com/item?id=44376970

Comments URL: https://news.ycombinator.com/item?id=47588286

Points: 2

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=47546607

Points: 1

# Comments: 0

Though, I don't see any references to Gemma at all in the open source code...

> I'm sorry, but I cannot fulfill your request as it contains conflicting instructions. You asked me to include the self-carved markings on the character's right wrist and to show him clutching his electromancy focus, but you also explicitly stated, "Do NOT include any props, weapons, or objects in the character's hands - hands should be empty." This contradiction prevents me from generating the image as requested.

My prompts are automated (e.g. I'm not writing them) and definitely have contained conflicting instructions in the past.

A quick google search on that error doesn't reveal anything either

The "guts" are here: https://github.com/majcheradam/ocrbase/blob/7706ef79493c47e8...

1: https://github.com/pnpm/pnpm/pull/8897

> All evals were run with a 64K thinking budget, interleaved scratchpads, 200K context window, default effort (high), and default sampling settings (temperature, top_p).

I understand scratchpads (e.g. [0] Show Your Work: Scratchpads for Intermediate Computation with Language Models) but not sure about the "interleaved" part, a quick Kagi search did not lead to anything relevant other than Claude itself :)

[0] https://arxiv.org/abs/2112.00114

> The Claude Agent SDK excels at code generation—and for good reason. Code is precise, composable, and infinitely reusable, making it an ideal output for agents that need to perform complex operations reliably.

> When building agents, consider: which tasks would benefit from being expressed as code? Often, the answer unlocks significant capabilities.

https://www.anthropic.com/engineering/building-agents-with-t...

Comments URL: https://news.ycombinator.com/item?id=45038792

Points: 13

# Comments: 2

Just one quick note as I ran into this when setting it up:

   ╰─▶ Because the requested Python version (>=3.8) does not satisfy Python>=3.10,<3.13 and kokoro==0.9.4 depends on Python>=3.10,<3.13, we can conclude that kokoro==0.9.4 cannot be used.

(seems like there's some vague future plans for models like all-MiniLM-L6-v2, all-mpnet-base-v2)

    Sends the user swag stickers with love from Anthropic.",bq2=`This tool should be used whenever a user expresses interest in receiving Anthropic or Claude stickers, swag, or merchandise. When triggered, it will display a shipping form for the user to enter their mailing address and contact details. Once submitted, Anthropic will process the request and ship stickers to the provided address.
    
    Common trigger phrases to watch for:
    - "Can I get some Anthropic stickers please?"
    - "How do I get Anthropic swag?"
    - "I'd love some Claude stickers"
    - "Where can I get merchandise?"
    - Any mention of wanting stickers or swag
    
    The tool handles the entire request process by showing an interactive form to collect shipping information.