claude.
7 writings found
Latest Archives
Reading Claude's System Prompts Like Code
Anthropic publishes Claude's system prompts with version history. What we can learn by diffing them, and what's still hidden.
Claude Fable 5.1: When Reasoning Effort Actually Matters
Testing Anthropic's new Fable 5.1 across reasoning levels reveals a wild cost/quality tradeoff. The pelican benchmark shows reasoning might not be what we think it is.
Claude Opus 4.8 and the Art of Admitting What You Don't Know
Exploring the honest AI upgrade that prioritizes Abstaining over hallucinating
What Claude Opus 4.8's 'Honesty' Update Actually Means for Developers
Anthropic's new model focuses on flagging uncertainties. Here's what this means for those of us building with AI.
I Built a Mac Presentation App in 45 Minutes Using AI Coding Agents
Vibe coding a native macOS presentation tool with Claude Code: what it means for engineers who want to expand beyond their comfort zones
Anthropic's Super Bowl Ad Started a War, and Nobody Looks Good
When Anthropic mocked ChatGPT's ads in a Super Bowl commercial, Sam Altman's meltdown revealed something more troubling about AI's future.
Claude 3, A Deep Dive into Anthropic's Latest AI Powerhouse
The world of large language models (LLMs) is in a constant state of evolution, and Anthropic's recent unveiling of Claude 3 marks a significant leap forward.