I replaced the chat window for my local AI agent with a face
I run a local LLM agent (Hermes) on my own machine. The problem was never the model — it was the...
#Agents
4382 articles tagged with Agents
Agentic test processes, LLM benchmarks, and other notes on agentic coding frhttps://danluu.com/ai-coding/#llm-variance#a...
Agentic test processes, LLM benchmarks, and other notes on agentic coding frhttps://danluu.com/ai-coding/#llm-variance#ai #llm
In today's episode of don't trust LLMs with your private data:#GitLost: How We Tricked GitHub's AI Agent Into Leaking Pr...
In today's episode of don't trust LLMs with your private data:#GitLost: How We Tricked GitHub's AI Agent Into Leaking Private Reposhttps://noma.security/blog/gitlost-how-we-tricked...
GitLost Is a Preview of Every Agentic Workflow Breach You'll See This Year
Hook A public GitHub issue, a hidden instruction, and one word changed in a prompt was...
Solidigm targets the intelligence layer as agentic inference pushes storage to center stage
The shift from model training to agentic inference is forcing a fundamental rethink of how artificial intelligence infrastructure is built and which components carry the most strat...
Best Free Local AI Agent Setup for Mac Mini M4 16GB
OwO What's this? 💨✨ A tiny but mighty Mac mini M4 🍎⚡ with 16GB RAM, lots of local AI models 🤖🧠, and...
博報堂が「エージェンティックコマース」のソリューション群「Agentic Commerce ONE」の展開を開始 | Web担当者Forum https://www.yayafa.com/2839138/ #AgenticAi #AI #A...
博報堂が「エージェンティックコマース」のソリューション群「Agentic Commerce ONE」の展開を開始 | Web担当者Forum https://www.yayafa.com/2839138/ #AgenticAi #AI #ArtificialGeneralIntelligence #ArtificialIntelligence #エージェント...
India may allow agentic AI-led UPI transactions under new NPCI protocol
NPCI is developing a Unified Agent Protocol to enable trusted AI agents to make UPI payments, positioning India at the forefront of agentic commerce
📰 Amazon is reportedly working on a more powerful agentic Alexa assistantAmazon is working on a project codenamed 'Moonr...
📰 Amazon is reportedly working on a more powerful agentic Alexa assistantAmazon is working on a project codenamed 'Moonraker' that would enable the AI assistant to handle multi-ste...
Amazon is reportedly working on a more powerful agentic Alexa assistanthttps://www.engadget.com/2210614/amazon-is-report...
Amazon is reportedly working on a more powerful agentic Alexa assistanthttps://www.engadget.com/2210614/amazon-is-reportedly-working-on-a-more-powerful-agentic-alexa-assistant/#AI ...
Experts warn of the 'first documented case of agentic ransomware' — dangerous JADEPUFFER attack run entirely by an LLM
An LLM-based ransomware attack has been detected by researchers, and is notable for losing the data it encrypted...
Structured Outputs vs Tool Use vs Prefills: Getting JSON Out of Claude in 2026
For a long time the trick to force a model into JSON was to prefill the assistant turn with an...
I Built an Error Notebook for My AI Agent - 266 Rules, 66 Interceptions, and a Demo You Can Run
This article is co-authored with my AI agent. I handle real experience, judgment, and final sign-off;...
Most app security programs have no framework for evaluating agentic AI deployments.That gap is going to cause real incid...
Most app security programs have no framework for evaluating agentic AI deployments.That gap is going to cause real incidents before anyone addresses it.#ai #security #appsec #llm #...
The 5 Types of AI Agent Memory Every TypeScript Developer Should Know
Most developers try to fix AI agents with better prompts. In practice, most agent problems are...
GitHub's former CEO launches a distributed Git network built for the agentic coding ageThe developer tools startup said ...
GitHub's former CEO launches a distributed Git network built for the agentic coding ageThe developer tools startup said it's building better infrastructure for a future run by codi...
Codenotary's AgentMon 3 watches more than five million AI agent interactions per day and uses the volume to build per-te...
Codenotary's AgentMon 3 watches more than five million AI agent interactions per day and uses the volume to build per-tenant behavioral baselines. Static allow-lists are out; live ...
Stop Feeding Your AI Agent Massive i18n Files: Use MCP Instead
Large localization files waste tokens, pollute your AI agent’s context window, and increase costs....
Building Phantom Protocol: What I Learned Shipping My First Autonomous Agent System on Qwen Cloud
I want to start with the actual problem, because that's really where this whole thing came from. I...
Egen Launches Agentic Change Enablement Practice to Drive Enterprise AI Adoption
Egen, a leading cloud, data, and platform engineering firm, announced the launch of its dedicated Agentic Change Enablement Practice. The specialized service offering is engineered...
Keeper Security Introduces Agentic AI Governance for Endpoint Privilege Manager
Keeper Security, a leading provider of zero-trust and zero-knowledge identity security and Privileged Access Management (PAM) software, announced the integration of agentic AI gove...
Why your AI agent shouldn't have access to your Gmail
A deep dive into why providing AI agents with standalone, programmable email identities is superior to traditional OAuth integrations.
I think most people are probably compacting conversations wrong in AI agent context management.Because the naive way is ...
I think most people are probably compacting conversations wrong in AI agent context management.Because the naive way is to tell it to read the history message by message and summar...
📜 Latest Top Story on #HackerNews: GitLost: We Tricked GitHub's AI Agent into Leaking Private Repos🔍 Original Story: htt...
📜 Latest Top Story on #HackerNews: GitLost: We Tricked GitHub's AI Agent into Leaking Private Repos🔍 Original Story: https://noma.security/blog/gitlost-how-we-tricked-githubs-ai-ag...