testing Elon in the middle of a trading round didn’t see that coming London Grand Final, Nov 14. Trade on Phantom Use PHANTOM code for 10% off @solana @phantom #phantom# #solana# #frontiertraders# #trading# #crypto# NFA · DYOR

Testing a different kind of thing today 🔥 I haven't worked with Windows in a while (10+ years). Curious to see what the Surface Ultra offers. > The Microsoft Surface Laptop Ultra uses an NVIDIA Blackwell RTX GPU built into the NVIDIA RTX Spark N1X superchip. I am obviously checking Perplexity Computer and Hermes, powered by local models like Nemotron and others. What else should I try to run there? 👀 I'm looking for recommendations to stress-test its performance running local workloads.

Testing for a Pixel 10, Galaxy Z Fold 6, or Nest Hub Max? Device Mode has them and more → Test how everything looks across modern devices. The new presets are grouped by form factor: Mobile, Foldables, Tablets & Desktops, and Smart Displays.

Testing AI agents isn't like testing regular software. The same input can produce a different output every run, there's rarely just one correct answer, and even a correct result can come from an "inappropriate" path. Title: The Most Common Questions About Agent Evals, Answered URL: ❓ Where should you even start? 💡 Pick one behavior to evaluate (say, whether a travel assistant books the requested date and price range), build a small dataset of 10-20 examples from your traces, run a baseline on your current version, and then keep adding failures you find in production or during development. ❓ What's the difference between offline and online evals? 💡 Offline evals run against a dataset before shipping and can compare against reference outputs, making them great for testing new prompts, models, or tools. Online evals score real production traces in real time, usually without reference outputs, relying on code checks and LLM judges to catch quality drift and surprises. ❓ How do you make an LLM judge actually trustworthy? 💡 Validate it against human scores on a small sample, phrase questions narrowly (like "did the reply mention every connecting flight?"), and score with a binary pass/fail or a few categories instead of a 1-10 scale. Picking a cheap judge model can also cut costs dramatically: one example dropped total judging cost from $28.17 with Claude Sonnet to just $0.34. ❓ How do you evaluate multi-turn conversations? 💡 A conversation can look fine turn by turn while still breaking down overall. The fix is to group turns by thread ID, display every message and tool call in order, and evaluate the whole thread with questions like "does the final booking reflect every change the user made?" #AIAgents# #Evals#