A data breach at Anthropic exposed internal documents detailing an unreleased AI model the company describes as its most powerful to date. Anthropic confirmed it is already testing the model with select customers, claiming significant advances in reasoning, coding, and cybersecurity. The breach resulted from a misconfiguration in Anthropic's content management system that automatically made ~3,000 uploaded files publicly accessible.
March 27, 2026
Chroma has released Context-1, a 20B parameter Mixture of Experts model trained specifically for retrieval tasks that require multi-hop reasoning. The model decomposes complex queries into subqueries, performs parallel tool calls, and actively prunes its own context mid-search—achieving comparable performance to frontier models at a fraction of the cost and up to 10x faster inference speed.
Google announced 'switching tools' that allow users to transfer chat histories and personal information directly into Gemini from competing chatbots like ChatGPT and Claude. The feature uses a prompt-based system for importing memories and accepts zip file uploads for chat logs. This move targets Gemini's lagging consumer adoption, which sits at 750 million monthly active users compared to ChatGPT's 900 million weekly active users.
Anthropic on Wednesday adjusted Claude's session limits for Free, Pro, and Max subscribers during peak demand hours (05:00-11:00 PT / 13:00-19:00 GMT). Users can now consume five hours of allowance in under five hours during these periods, while off-peak usage maintains standard pacing. Approximately 7% of Pro tier users will hit limits they previously wouldn't have encountered.
Continue released v1.0.65 for JetBrains IDEs and v1.3.36 for VS Code, focusing on stability fixes. The update addresses IDE freezing issues in JetBrains, adds compatibility with DeepSeek's reasoning model, and fixes multiple memory leaks and crash conditions.
Google is launching "Import Memory" and "Import Chat History" features in Gemini that let users transfer their preferences and past conversations from other AI chatbots. The tools use copy-paste prompts and .zip file uploads to help users avoid retraining a new AI model on their preferences.
Apple has secured full access to Google's Gemini models within its data centers and is using knowledge distillation to generate training data for smaller, on-device AI models. The approach allows Apple to create lightweight versions that replicate Gemini's reasoning patterns while running directly on Apple devices, requiring significantly less processing power.
Mistral has released Voxtral TTS, a 4-billion-parameter text-to-speech model that can clone voices from just three seconds of reference audio across nine languages. The model delivers 70ms latency for typical 10-second samples and outperformed ElevenLabs Flash v2.5 in naturalness tests. Voxtral is available via API at $0.016 per 1,000 characters and as open-weights on Hugging Face.
Google is rolling out chat and memory import functionality to Gemini, allowing users to transfer conversation history from ChatGPT, Claude, and other AI apps. The feature supports zip file uploads up to 5 GB, with users able to upload up to 5 files per day. A companion memory import tool lets users generate context summaries from other chatbots to paste into Gemini.
Google is expanding Search Live, its voice and camera-based AI search assistant, to more than 200 countries and territories with support for dozens of languages. The expansion is powered by Gemini 3.1 Flash Live, a new audio-focused model that Google claims offers faster response times and more natural conversations.
Google is rolling out Search Live globally, its conversational search feature powered by Gemini 3.1 Flash Live, which supports over 90 languages. Simultaneously, Google Translate's live headphones translation mode is launching on iOS after its Android debut, supporting over 70 languages across seven new countries.
Google has begun globally rolling out Search Live, enabling users in 200+ countries and territories to point their phone camera at objects and ask questions about what they see. The expansion is powered by Google's Gemini 3.1 Flash Live model, designed to be natively multilingual with faster, more reliable performance.
Google has released Gemini 3.1 Flash Live, its new voice and audio AI model, scoring 95.9% on the Big Bench Audio Benchmark at high thinking levels—second only to Step-Audio R1.1 Realtime at 97.0%. Response times range from 0.96 seconds at minimal thinking to 2.98 seconds at high thinking, with pricing held at $0.35 per hour of audio input and $1.40 per hour of audio output.