ai-agents.
72 writings found
Latest Archives
Trust is the Missing Ingredient in AI Agent Security
The 2026 Stack Overflow survey reveals only 7% of developers trust AI for important decisions. Here's why Docker's pivot to sandboxes matters for production agents.
Google Antigravity Shows How AI Agents Transform Scientific Discovery
Google's agentic platform compresses drug discovery workflows into single sessions, combining protein prediction, structural analysis, and literature synthesis for antimicrobial research.
AI Agents in the Wet Lab: Closing the Gap Between Theory and Biology
Google researchers are deploying AI agents to automate molecular discovery with real-time feedback loops, discovering nanomolar protein binders and reshaping how we approach drug discovery.
Google Antigravity: AI Agents Finally Making Biology Faster
How Google's agentic platform is compressing weeks of antibiotic discovery into single sessions using ProtNLM and structural analysis.
Google Antigravity: How AI Agents Are Accelerating Drug Discovery
Google's agentic science platform compresses weeks of biological research into single sessions, using AI to discover novel antibiotics from protein databases.
Human-on-the-Loop: How AI Agents Shift Engineering from Execution to Ownership
Meta's Forum app reveals how treating AI as a loop participant rather than autocomplete changes what engineers actually do. Verification, not generation, is the real multiplier.
LFM2.5-24B: The MoE That Punches Above Its Weight Class
A compact 24B MoE model that dominates tool use and agentic tasks while running efficiently on consumer hardware. What this means for local AI deployments.
Docker's Agent Sandbox Strategy: What Developers Need to Know
Docker's new Cloud Sandboxes and Kit specification represent a fundamental shift in how we deploy and govern AI agents. Here's what it means for your workflow.
Why Your AI Agent Passed Once But Failed 19 Times
ThinkingBox reveals agents pass single attempts but fail on repeat. 67% of failures look clean. The gap between capability and consistency is the real problem.
Why AI Agents Need Hard Budget Caps by Default
As coding agents become more autonomous, hard budget limits aren't optional anymore. They're a safety requirement for developers and enterprises alike.
Meta Opens Muse to Builders: DIY AI Agents Are Here
Meta open-sourced Muse, letting developers build custom AI gadgets on ESP32 and Raspberry Pi. What this means for the future of edge AI.
Meta Open Sources Muse: Build Your Own AI Agent Hardware
Meta releases open source Muse AI agent SDKs for ESP32 and Raspberry Pi, letting developers build custom smart home gadgets. What this means for the future of AI hardware.
The Trade-off Between Type Safety and AI Agent Tooling
Exploring how Skip Labs balances programming language design with practical constraints for building cost-effective AI agent infrastructure.
OpenAI DevDay 2024: Dots, Ultrafast Models, and the Agent Era
Live coverage of OpenAI's keynote announcing Dots personal agents, GPT-6.1 Sol, Ultrafast inference, and ChatGPT Sites at DevDay 2024.
Gemini 3.8 Live Avatar: The Next Frontier for Enterprise AI Agents
Google's Live Avatar brings realistic visual presence to conversational AI with lip-sync, multilingual support, and asynchronous tool calling for enterprises.