Fable's judgement

kept by eddie jul 06

The author learned to let Claude Code's Fable model use its own judgement to delegate coding tasks to lower-power models, improving efficiency and token usage.

Why I believe in SOTA models over custom ones
The future of AI is powerful general models becoming cheaper, not narrow custom models, because specialized tasks still benefit from broad intelligence.
also on Haiku, Sonnet, Opus, #developer-tools
Hyperproductivity: The Next Stage of AI? - by Steve Newman
Hyperproductive software teams build AI tools that automate their work and improve themselves, achieving compounding productivity gains that may foreshadow broader AI impact.
also on Jesse Vincent, Claude Code, #ai-agents, #ai-coding, #developer-tools
Computer use is 45x More Expensive Than Structured APIs
Vision-based computer use agents are 45x more expensive and much slower than structured APIs for internal tools, requiring detailed walkthroughs to succeed.
also on Haiku, #developer-tools
Claude's Voice Mode Just Got Smarter
Anthropic updated Claude’s voice mode to use Sonnet/Opus models, add Gmail/Slack context, and improve language support, while noting its turn‑based design limits naturalness.
also on Sonnet, Opus, #productivity, #developer-tools
Autoresearch, Claude and Constrained Optimization
An experiment using Claude Code to autonomously optimize a file compression algorithm over 10 iterations, achieving competitive results against standard tools by iterating on an LZSS-based approach.
also on Sonnet, Claude Code, #automation, #ai-coding, #developer-tools