Cohere's Compass Beats Google and Amazon Searching Video by Exact Moment
Cohere adds timestamped video search to Compass, outperforming video-native embeddings from Amazon, Google, and Qwen on an 11-dataset retrieval suite.
20 stories
Cohere adds timestamped video search to Compass, outperforming video-native embeddings from Amazon, Google, and Qwen on an 11-dataset retrieval suite.
A Rust rewrite shrinks the agent-to-browser bridge by 23x and 25x on memory, dropping Playwright as a runtime dependency.
Black Forest Labs teams with RTL Deutschland, Nura Studios, and Studio Babelsberg for a global AI film contest with over $25,000 in prizes.
Artificial Analysis launched a Time to First Audio benchmark for text to speech models, showing streaming systems answer in under 400 ms while non-streaming peers take 2 seconds.
OpenAI hands Apollo, METR, Transluce, and Goodfire deep access to internal models, training runs, and interpretability tooling to stress-test alignment.
Perplexity spins up a dedicated lab chasing autonomous research agents, backed by 10,000+ GPUs and open releases of models, code, and benchmarks.
Liquid AI's d1.2 and d1.2-ultra top the Artificial Analysis Decision Index with audio input, five new structured output tasks, and near-perfect calibration.
Sarvam AI opens its India-hosted inference stack to everyone, undercutting global providers on price while matching them on speed across frontier open-weight models.
Sakana AI releases JFinBench, a 321-question Japanese finance benchmark built from 2026 certification exams that exposes a persistent gap between open-weight and proprietary models.
Tencent's Hy4 flash packs 224B total parameters with 12B active, matches Claude Haiku 5.5 on daily tasks at 1/18th the cost
Alibaba's new flagship uses a fresh MoE design to cut token usage nearly in half while beating Qwen3.8-Max on productivity benchmarks.
Databricks now lets teams define business metrics once in Unity Catalog and publish them directly to Power BI semantic models, keeping definitions in sync.
Perplexity's new open-weight classifiers return calibrated probabilities instead of text, land on the cost-capability Pareto frontier, and add span extraction.
Artificial Analysis refreshed its Coding Agent Index with a harder FrontierCode 2.0 and tightened Terminal-Bench 4.1, reshuffling the leaderboard and dropping average scores by five points.
Anthropic rolled out custom theming for Claude Code in the desktop app, letting you restyle colors and drop in animated backdrops through mods.
Anthropic ships a proactive coordinator, shareable read-only threads, reminders, and /btw and /fork slash commands to Claude Code Projects.
Artificial Analysis introduces WDER-based diarization scoring across 97 multi-speaker conversations, with Nvidia's Nemotron 3.5 Transcribe topping the chart at 3.3%
Browser Use agents can now log into any site through 1Password without the model ever seeing the password, using an approval flow on your own device.
Google Antigravity's new /run-workflow command has the agent write a Python script that orchestrates parallel and sequential subagents with structured handoffs.
Perplexity extends its persistent agent product to the Mac desktop, letting Max subscribers delegate long-running jobs across engineering, marketing, QA, and legal.