Why AI benchmarks keep lying to you
Leakage runs from 1% to 45% on popular benchmarks, and even Meta found 16% of MMLU contaminated. The scores measure memory as much as ability.
Read More
Author: Rundowns AI Desk
AI model pricing compared: same benchmark, five times the bill
Grok 4.6 and GPT-5.6 Sol Max tie at 61 on the AA index. One charges $6 per million output tokens, the other $30. The maths of that gap.
Read More
Meta open-sources a 30B model and teases a stronger one
Muse Glimmer ships under Apache 2.0, sized for consumer hardware. Zuckerberg paired it with a 6,500-word case against closed AI.
Read More
Nvidia guarantees its own chips to unlock $500B in AI financing
Six private capital giants signed non-binding MOUs. Nvidia backs the collateral value itself, against hardware it controls the obsolescence of.
Read More
IBM bets thousands of consultants on OpenAI’s models
IBM is folding GPT-5.6, Codex and ChatGPT Work into its consulting platform and building a dedicated OpenAI practice. Terms undisclosed.
Read More
Grok 4.6 matches GPT-5.6 Sol on benchmarks at a fifth the output price
Grok 4.6 scored 61 on the AA Intelligence Index, level with GPT-5.6 Sol Max, while charging $6 per million output tokens against $30.
Read More
Anthropic starts watermarking Claude’s text, and users aren’t happy
Every model after 2 August carries an invisible mark. It proves processing, not authorship. And nobody will say how much editing removes it.
Read More
Databricks raises $5B at a $190B valuation, up 42% in six months
Coatue led the round. Run-rate revenue passed $7B with 80%+ growth. But the multiple expanded faster than the business.
Read More
AI scaling laws: has bigger stopped meaning better?
The curves have not broken. The recipe changed twice, the spending moved to inference, and the data stock has a date on it.
Read More
Context windows explained: what a million tokens actually changes
Advertised context and usable context are not the same number. What a million-token window actually buys you, and what it does not.
Read More
What Is Retrieval-Augmented Generation (RAG) and When Do You Need It?
How retrieval-augmented generation works, the two places it breaks, and when long context or a plain SQL query would serve you better.
Read More
How to Write Better AI Prompts: 12 Techniques That Actually Work
Twelve prompting techniques that have an actual mechanism behind them. And how to tell when prompting has hit its ceiling.
Read More