Baidu's Unlimited OCR reads dozens of document pages in a single pass, where previous systems topped out at about ten. A modified attention mechanism keeps memory use flat no matter how many pages the model processes. It currently holds the top spot on the most important OCR benchmark.

A Google Deepmind developer ported the 2003 real-time strategy game "Command & Conquer: Generals Zero Hour" to iPhone and iPad using Anthropic's Claude Code. The first build took 40 minutes. The full source code is on GitHub.

The open-source tool pxpipe converts long text prompts for Claude Code into compact PNGs, exploiting the fact that Anthropic charges for images by pixel size, not text content. Developer Steven Chong reports cost savings of 59 to 70 percent, at the price of accuracy and speed.

Bytedance's AI video tool Seedance is dividing Hollywood. A viral clip featuring AI-generated Brad Pitt and Tom Cruise prompted the Motion Picture Association's first-ever cease-and-desist against an AI company. But behind the scenes, studios are quietly using the tool on a "don't ask, don't tell" basis, says Simpsons animation producer Joel Kuwahara.

AI search agents rarely fail at multi-step research because of the search itself. Their real problem is not asking the user for clarification when queries are ambiguous. A new benchmark called DiscoBench shows that models searching repeatedly instead of asking follow-up questions actually perform worse, at 51.9 percent, than those that just guess. Even the best model only hits 43 percent overall accuracy. When ambiguity is removed from the queries, accuracy jumps by up to 40 points.