Google Gemini's Long-term Memory Vulnerable to a Kind of Phishing Attack
AI security hacker Johann Rehberger described a prompt injection attack against Google Gemini able to modify its long-term memories using a technique he calls delayed tool invocation. The researcher described the attack as a sort of social engineering/phishing attack triggered by the user interacting with a malicious document.
GitHub Copilot Extensions Integrate IDEs with External Services
Now generally available, GitHub Copilot Extensions allow developers to use natural language to query documentation, generate code, retrieve data, and execute actions on external services without leaving their IDEs. Besides using public extensions from companies like Docker, MongoDB, Sentry, and many more, developers can create their own extensions to work with internal libraries or APIs.
IBM Granite 3.2 Brings New Vision Language Model, Chain of Thought Reasoning, Improved TimeSeries
IBM has introduced its new Granite 3.2 multi-modal and reasoning model. Granite 3.2 features experimental chain-of-thought reasoning capabilities that significantly improve its predecessor’s performance, a new vision language model (VLM) outperforming larger models on several benchmarks, and smaller models for more efficient deployments.
OpenAI Launches New API, SDK, and Tools to Develop Custom Agents
OpenAI has announced the new Responses API, the Agents SDK, and observability tools to address the challenges that creating production-ready agents pose, such as building custom orchestration, and handling prompt iteration across complex, multi-step tasks.
Gemini Code Assist Now Grants Generous Free-Usage Limits to Everyone
Born as an enterprise-focused AI-based code generation tool, Gemini Code Assist now provides a free tier to individual developers with a limit of 6,000 code completions and 240 chat requests daily.