Skip to content
TopicTracker
From HackerNewsView original ↗
TranslationTranslation

Model and effort in Claude Code: knowing more vs. trying harder

The article explores the distinction between model capability (knowledge) and effort (computational persistence) in Claude Code, discussing how the system balances inherent reasoning power with iterative problem-solving to improve coding outcomes.

Background

- This is a post from Anthropic (the AI company behind Claude) discussing the difference between "knowing more" (training a better model) vs. "trying harder" (using more inference compute at runtime) in the context of Claude Code, their coding agent product.

Related stories

  • Better Models: Worse Tools

    7.5

    Newer Claude models sometimes invent extra keys in tool call arguments, breaking validation in Pi's edit tool. The author suspects post-training for Claude Code's forgiving harness makes alternative schemas fail. This suggests closed RL training can degrade general tool-use reliability.

  • llm-coding-agent 0.1a0

    2.0

    Simon Willison released llm-coding-agent 0.1a0, an experimental coding agent built on his LLM library. The agent provides tools for reading, editing, searching files and executing commands, and ships with a Python API and CLI. It was developed using Claude Code (Fable 5) via TDD with a spec-first approach, and is available as a slop-alpha on PyPI.

  • Truth Social Is Still Just Trump’s Blog

    2.0

    Truth Social remains an outlet primarily for Trump's own posts, while other administration officials continue using X. The platform functions as a blog-like channel for Trump's messages rather than a genuine social network competitor.