Artificial Intelligence — Page 2
425 articles in this category
Surogate Speech: What Its Local Romanian Models Offer
Surogate Speech pairs 116M-parameter recognition with Romanian text-to-speech and three voices. Explore local hardware options and noncommercial terms.
Microsoft Copilot: What Home, Code and Autopilot Add
Microsoft Copilot adds three ways to work: Home, Code and Autopilot. Here is what each does, how app hosting works and when previews start arriving.
Google AI Video Research Tackles Continuity Across Scenes
Google outlines 4 research frameworks for longer AI videos, combining creative planning, visual memory and feedback to keep scenes more consistent.
Claude Agents Find a CRISPR-Like Enzyme System in 21 Hours
About 950 Claude agents screened 200,000+ enzymes in 21 hours and flagged ART, a new CRISPR-like system Anthropic's lab has now started to test.
Transformers Now Runs GGUF Quants on Mac at llama.cpp Speed
Hugging Face Transformers can now run GGUF quants packed on Apple Silicon. A Qwen3.5-4B Q4_K_M model shrinks from 8.42GB to 2.74GB. Here's how it works.
Gemini 3.8 Flash TTS: What Prompt-Built AI Voices Can Do
Gemini 3.8 Flash TTS and Flash-Lite TTS let developers design new AI voices from a text prompt in 100+ languages. Here's what both models can do.
Ternary Bonsai 2 27B: A 5.9GB Model for 16GB Laptops
Ternary Bonsai 2 27B squeezes Qwen3.8-27B into 5.9GB with 1.76-bit weights and keeps 98.2% of its benchmark score. Here's how to run it locally.
GPT-6 Sol vs Luna vs Astra: Which Model Should You Use?
GPT-6 Sol costs $2 per million input tokens and Luna $0.10, half of GPT-5.6's current rates. Here's how they compare with Astra and how to migrate.
Claude Opus 5.5 Pricing, Benchmarks and When to Switch
Claude Opus 5.5 lands at $4 per million input tokens — 20% below Opus 5 — and tops Artificial Analysis's independent intelligence index at 58.
Xiaomi MiMo-V2.6 Pro: What the Top Open Model Offers
Xiaomi MiMo-V2.6 Pro scores 46 on the Artificial Analysis index, the best open-weight result yet, with MIT-licensed weights and $0.87 output pricing.
Run Local LLMs on a Mac: MLX and oMLX Step-by-Step Guide
A step-by-step guide to running local LLMs on Apple Silicon with mlx-lm and oMLX: install, chat, 4-bit quantize and serve an API on port 8000.
Grok 4.7 in GitHub Copilot: What Changes for Developers
Grok 4.7 lands in GitHub Copilot on day one at $2 per million input tokens, with SpaceXAI reporting 71% on DeepSWE and a stronger agentic coding loop.
StepFun Step 5 Preview: 600B MoE Agent Model at $1 Input
StepFun's Step 5 Preview pairs 600B parameters with 27B active and a 1M-token context at $1 per million input tokens, with open weights due October 15.
Astra for Law Adds a Verified Case Law Index
OpenAI's Astra for Law pairs GPT-6 with a 230-million-URL legal index and scored 54% on Vals AI's research benchmark, up from 38.7% on web search.
Agentic Code Migration: GitHub's 800K-Line Rust Port
GitHub's coding agents rewrote 430,000 lines of TypeScript into 832,000 lines of production Rust in 14.5 weeks, at a 96% prompt-cache hit rate.
Jev Is a New AI Model That Answers in Probabilities
TypeSafe AI's Jev skips text generation entirely and returns calibrated probability scores instead, priced at $0.042 per million input tokens.
Google CC Becomes an AI Agent for Whole Households
Google Labs expanded CC into a shared family AI agent for up to six people, with a household memory that separates group facts from personal ones.
Paper2Agent Turns Research Papers Into AI Agents
Stanford's Paper2Agent rebuilds papers as agents that rerun their own analyses. It turned 74 of 100 computational biology papers into working agents.
Life Sciences Verification Opens Claude to Bio Labs
Anthropic's Life Sciences Verification Program gives vetted research teams Claude access tuned for biology, with monitoring replacing live blocking.
Firefox Smart Window Runs Mistral Small 4 Privately
Mozilla's Firefox Smart Window beta now runs on Mistral Small 4 in North America and France, under a zero data retention agreement with no saved chats.
AI Data Centers Learn to Flex Power for the Grid
Emerald AI, Google and NVIDIA launched the AI Energy Management Alliance with 18 partners, saying flexible data centers could unlock 100 GW from the grid.
Claudeforce Beta Puts 37 Salesforce Skills in Claude
Claudeforce moved to open beta at Dreamforce '26, putting 37 prebuilt Salesforce sales skills and live CRM data inside Claude with permissions intact.
Gemini 3.8 Live Adds Reasoning to Real-Time Voice AI
Google's new Gemini 3.8 Live models reason mid-conversation across 97 languages and top the speech quality index at 82.6. Here is what changes.
Perplexity Portable Computer Runs Local AI on Windows
Perplexity's on-device agent now runs on Windows PCs with 24GB+ RTX GPUs, keeping the model, harness, orchestrator and scheduler off the cloud.