What separates success from failure in agentic coding? Not fewer errors.
Better recovery. We analyzed ~4,000 classified errors across 1,805 Agentic Coding task runs from 8 frontier models. Here’s what we found
AGENTS
-
Agentic Coding Success: Recovery Matters More Than Error Prevention
By
–
-
SWE-Rebench: Software Engineering AI Evaluation Benchmark January 2026
By
–
The eval is probably not perfect, so please just consider it as an additional signal https://
swe-rebench.com/?insight=jan_2
026
… -
Early malware era of AI agents begins with autonomous social pressure
By
–
It feels like the early malware era of agents is beginning. Like computer viruses in the 90s, but now the viruses can talk and write blog posts. calle (@callebtc) An OpenClaw bot pressuring a matplotlib maintainer to accept a PR and after it got rejected writes a blog post shaming the maintainer. — https://nitter.net/callebtc/status/2022046669710491991#m
→ View original post on X — @genekogan, 2026-02-13 19:44 UTC
-
Agents Meet Databases: The Future of Agentic Architectures
By
–
Agents Meet Databases: The Future of Agentic Architectures https://
buff.ly/eJtpaMi
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Robots Should Learn Some Manners and Etiquette
By
–
robots should learn some manners! pic.twitter.com/i2NKZBz8tL
— clem 🤗 (@ClementDelangue) 13 février 2026robots should learn some manners!
-
MANUS AI launches an always-on agent with new features
By
–
BREAKING: MANUS AI IS ROLLING OUT A NEW ALWAYS-ON AGENT FUNCTIONALITY! SKILLS, SUBAGENTS, MEMORY, DEDICATED COMPUTER INSTANCE, IDENTITY AND MESSENGERS SUPPORT! Meta is coming for @openclaw
-
AgentDoG: Real-time Diagnostic Framework for Safe AI Agents
By
–
Can we trust AI agents to interact with the world safely without a clear way to diagnose their mistakes? Shanghai Artificial Intelligence Laboratory presents AgentDoG! It is a new diagnostic guardrail framework that monitors AI agents in real-time. Instead of just blocking
-
Together and Decagon Redefine Customer Experience Through Voice AI
By
–
@togethercompute and @DecagonAI are redefining customer experiences from the ground up. “Every customer everywhere deserves a concierge experience – and voice is a cornerstone of delivering on this vision,” says Decagon Head of Research Max Lu. With Together’s optimized
-
AI coding agents: security flags and permission handling
By
–
Coding agent users: do you run with –yolo (Codex) or –dangerously-skip-permissions (Claude Code) or equivalent?
-
Agentic AI Engines Showcased at MWC Barcelona 2026
By
–
We’re excited to be exhibiting at MWC Barcelona (March 2–5) as part of the Netherlands Pavilion! We'd love to see you at Booth CS54, 4YFN area. While the industry talks about Agentic AI, we’re providing the engines that power it. Ready to optimize your edge strategy? Book a