Upvote 3 Hybrid Reasoning Agents: Which Monitor Still Works A third of the steps go silent, the bill drops 2.7x, and the monitoring test only asked whether math answers were right. Adham Khaled · Agents · 6 days ago ·
Upvote 1 AI Code Verification: What a Passing Check Proves One shared error pulled three of OpenAI's math papers. Write the sentence your check proved under the claim you meant. Adham Khaled · Reasoning · Nov 3 ·
Upvote 1 When to use DeepSeek-V4.1-Flash Field-test, Max effort, private repo to 512k. Reading 60/64 each. Kimi 8/8 vs DeepSeek 7/8 repairs. Bill $1.70 vs $31.75 Adham Khaled · LLMs · Oct 1 ·
Upvote 15 Bot Sitting: When to Trust / Review AI Agent Code Five settings for agent PRs, the rule that picks between them, and the paths that never get Full auto Adham Khaled · Development · Aug 13 ·
Upvote 3 Model Routing Layers and the Prompt Cache Tax One model switch cost 5x a warm turn at 10,000 tokens and 11x at 60,000, measured across three session sizes. Adham Khaled · Development · Jul 29 ·