Thoughts on AI, LLMs, building products, and the developer tools I use every day.https://appdeployed.com/en-ushttps://appdeployed.com/blog/gpt-54-agent-tool-use-benchmarks/https://appdeployed.com/blog/gpt-54-agent-tool-use-benchmarks/Early benchmarks on GPT-5.4 show 15–20% better multi-step tool use accuracy and stronger few-shot agent learning. Worth testing against your current stack.Sat, 30 May 2026 00:00:00 GMTAILLMsOpenAIProducthttps://appdeployed.com/blog/grok-v9-medium-training-complete/https://appdeployed.com/blog/grok-v9-medium-training-complete/xAI completed training on Grok V9-Medium, a 1.5T-parameter model targeting coding and agentic tasks. Expected public release: mid-June 2026.Sat, 30 May 2026 00:00:00 GMTAILLMsToolshttps://appdeployed.com/blog/claude-4-what-builders-need-to-know/https://appdeployed.com/blog/claude-4-what-builders-need-to-know/Anthropic's Claude 4 family raises the bar on reasoning, tool use, and context length. Here's what changes for developers building AI-powered products.Thu, 28 May 2026 00:00:00 GMTAILLMsAnthropichttps://appdeployed.com/blog/building-ai-apps-that-actually-ship/https://appdeployed.com/blog/building-ai-apps-that-actually-ship/Most AI prototypes die in demo mode. Here's the decision framework I use to take a product from 'cool demo' to deployed — and what I've learned building Orion, the HBS Campus Guide, and other live apps.Fri, 15 May 2026 00:00:00 GMTAIProductDevelopmenthttps://appdeployed.com/blog/gpt-5-vs-claude-4-a-builders-comparison/https://appdeployed.com/blog/gpt-5-vs-claude-4-a-builders-comparison/I've run both models through the same real-world tasks I use in production. Here's an honest comparison — not benchmarks, but what matters when you're shipping a product.Tue, 05 May 2026 00:00:00 GMTAILLMsOpenAIAnthropic