Tag: agent

Source URL: https://lethain.com/our-own-agents-our-own-tools/ Source: Irrational Exuberance Title: Our own agents with their own tools. Feedly Summary: Entering 2025, I decided to spend some time exploring the topic of agents. I started reading Anthropic’s Building effective agents, followed by Chip Huyen’s AI Engineering. I kicked off a major workstream at work on using agents, and I…

Simon Willison’s Weblog: Constitutional Classifiers: Defending against universal jailbreaks

—

by

Source URL: https://simonwillison.net/2025/Feb/3/constitutional-classifiers/ Source: Simon Willison’s Weblog Title: Constitutional Classifiers: Defending against universal jailbreaks Feedly Summary: Constitutional Classifiers: Defending against universal jailbreaks Interesting new research from Anthropic, resulting in the paper Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming. From the paper: In particular, we introduce Constitutional Classifiers, a framework…

Cloud Blog: CVE-2023-6080: A Case Study on Third-Party Installer Abuse

—

by

Source URL: https://cloud.google.com/blog/topics/threat-intelligence/cve-2023-6080-third-party-installer-abuse/ Source: Cloud Blog Title: CVE-2023-6080: A Case Study on Third-Party Installer Abuse Feedly Summary: Written By: Jacob Paullus, Daniel McNamara, Jake Rawlins, Steven Karschnia Executive Summary Mandiant exploited flaws in the Microsoft Software Installer (MSI) repair action of Lakeside Software’s SysTrack installer to obtain arbitrary code execution. An attacker with low-privilege access…

Bulletins: Vulnerability Summary for the Week of January 27, 2025

—

by

Source URL: https://www.cisa.gov/news-events/bulletins/sb25-034 Source: Bulletins Title: Vulnerability Summary for the Week of January 27, 2025 Feedly Summary: High Vulnerabilities PrimaryVendor — Product Description Published CVSS Score Source Info 0xPolygonZero–plonky2 Plonky2 is a SNARK implementation based on techniques from PLONK and FRI. Lookup tables, whose length is not divisible by 26 = floor(num_routed_wires / 3) always…

The Register: OpenAI unveils deep research agent for ChatGPT

—

by

Source URL: https://www.theregister.com/2025/02/03/openai_unveils_deep_research_agent/ Source: The Register Title: OpenAI unveils deep research agent for ChatGPT Feedly Summary: Takes a bit more time to spout a bit less nonsense OpenAI today launched deep research in ChatGPT, a new agent that takes a little longer to perform a deeper dive into the web to come up with a…

AlgorithmWatch: As of February 2025: Harmful AI applications prohibited in the EU

Feb 1, 2025

—

by

Source URL: https://algorithmwatch.org/en/ai-act-prohibitions-february-2025/ Source: AlgorithmWatch Title: As of February 2025: Harmful AI applications prohibited in the EU Feedly Summary: Bans under the EU AI Act become applicable now. Certain risky AI systems which have been already trialed or used in everyday life are from now on – at least partially – prohibited. AI Summary and…

New York Times – Artificial Intelligence : A Look at OpenAI’s Operator, a New A.I. Agent

Feb 1, 2025

—

by

Source URL: https://www.nytimes.com/2025/02/01/technology/how-helpful-is-operator-openais-new-ai-agent.html Source: New York Times – Artificial Intelligence Title: A Look at OpenAI’s Operator, a New A.I. Agent Feedly Summary: Operator, a new computer-using tool from OpenAI, is brittle and occasionally erratic, but it points to a future of powerful A.I. agents. AI Summary and Description: Yes Summary: The text discusses “Operator,” a…

Hacker News: Auto-Differentiating Any LLM Workflow: A Farewell to Manual Prompting

Feb 1, 2025

—

by

Source URL: https://arxiv.org/abs/2501.16673 Source: Hacker News Title: Auto-Differentiating Any LLM Workflow: A Farewell to Manual Prompting Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses LLM-AutoDiff, a novel framework aimed at improving the efficiency of prompt engineering for large language models (LLMs) by utilizing automatic differentiation principles. This development has significant implications…

The Register: Google to Iran: Yes, we see you using Gemini for phishing and scripting. We’re onto you

Jan 31, 2025

—

by