Browsing Tag
ai
1833 posts
Beyond the Chat Box: OpenAI’s OS-level Agent and Its Plaintext Problem
The agent is leaving the chat window and moving into the operating system. OpenAI’s new “Computer History” feature…
Why WhatsApp voice notes break general-purpose transcription
Most speech-to-text is benchmarked on audio that looks nothing like a WhatsApp voice note. The standard evaluation sets…
The Fundamentals of AI Engineering – EP 01
AI Engineering means using an existing AI model to add useful AI features to a real software application.…
Prompt injection: your customer-facing AI is an attack surface
Here is a fun little exercise. Imagine you hired a brilliant, tireless, endlessly polite support rep. They memorized…
Anthropic Expands Scientist Access to Frontier Models Through a Staged Biology Program
Anthropic is building a staged access path for life-science researchers to use its frontier AI systems. The company…
OpenAI GPT-5.6 Launch Reshapes Its Model Line With Sol, Terra and Luna
OpenAI has rolled out the GPT-5.6 family, introducing three models intended to cover advanced professional work, balanced deployments…
Agent-Scoped Memory in Deep Agents: Sharing Memory Across Conversations
In the previous article, we looked at user-scoped memory, where each user gets their own private long-term memory.…
CrossSessionMemoryGuard: vigilando la exfiltración de memoria cross-session en agentes multi-tenant
CrossSessionMemoryGuard: vigilando la exfiltración de memoria cross-session en agentes multi-tenant TL;DR Los agentes con memoria persistente compartida entre…
The Agent Left the IDE
The most interesting thing about AI coding agents right now is not that they can write code. It…
Healthcare Software Testing for Clinical AI and Safer Releases
AI is moving into clinical workflows and changing the scope of healthcare QA. This blog explains how organizations…
