Workshop Log
Build logs, experiment notes, and dispatches from the workshop floor.
AI digest: Hardware wars heat up
Taalas ditches GPUs for hardwired AI chips, Pentagon summons Anthropic CEO, and ByteDance cracks the reasoning code.
ai-newsdigesthardwaremilitary-ai
MCP servers: giving AI models actual superpowers
The Model Context Protocol lets you plug tools into Claude like USB devices. Tested a few.
mcpclaudetool-useprotocol
DeepSeek R1 vs Claude 3.5: a head-to-head on real tasks
Ran both models through the same set of coding and reasoning tasks. Results were closer than expected.
deepseekclaudebenchmarkscomparison
Building an agent loop with Claude and tool use
Wired up Claude with tool calling to build a basic autonomous agent. Simpler than expected.
claudeagentstool-useanthropic-api
Testing Kimi k1.5: the reasoning model nobody's talking about
Moonshot AI's Kimi k1.5 quietly dropped and it's genuinely impressive on long reasoning tasks.
kimireasoningbenchmarksmoonshot-ai