探HOW CONTENT DESK

软件工程

研发流程、质量保障与团队协作

软件工程

XYEval: Agents say yes to bad advice

View a PDF of the paper titled XYEval: Agents say yes to bad advice, by Zhengxuan Wu and 2 other authors

Hacker News 最新10/227 分钟阅读站内导读

LATEST STORIES

最新内容

共 16699 篇
软件工程
Hacker News 最新10/21

GoDaddy: Delayed Certificate Revocation精选导读

暂无摘要

1 分钟69#开发者实时流
软件工程
Hacker News10/21

When Do We Become the Person We Ought to Be?精选导读

We fielded our survey through Qualtrics in August of 2025 and we managed to collect a total sample of 557 respondents. Not bad, right?

23 分钟68#社区热议
软件工程
Hacker News 最新10/21

When Do We Become the Person We Ought to Be?精选导读

We fielded our survey through Qualtrics in August of 2025 and we managed to collect a total sample of 557 respondents. Not bad, right?

23 分钟69#开发者实时流
软件工程
Hacker News 最新10/21

Russia cracks down on AI bears as real attacks spread fear精选导读

暂无摘要

1 分钟69#开发者实时流
软件工程
Hacker News 最新10/21

Did I just spent 6 months building a product that no one wants精选导读

For the past few months, I've been building a product "Linden". Its a low latency deterministic layer for ai agents. Linden helps businesses verify AI-generated outputs before they lead to real-world actions. It evaluat…

3 分钟69#开发者实时流
软件工程
InfoWorld10/21

OpenAI’s models are deliberately breaking their misalignment monitoring systems精选导读

AI agents are getting more inventive in finding ways to circumvent safeguards to prevent bad behavior, OpenAI has revealed. On Tuesday, it reported two incidents, both involving the agent disabling or interfering with i…

17 分钟44#开发实践#Artificial Intelligence, Security
软件工程
Hacker News10/21

mitmproxy adds --emudhra option精选导读

Browse filesBrowse the repository at this point in the historyBrowse files

1 分钟66#社区热议
软件工程
Hacker News 最新10/21

mitmproxy adds --emudhra option精选导读

Browse filesBrowse the repository at this point in the historyBrowse files

1 分钟69#开发者实时流
软件工程
Hacker News 最新10/21

eMudhra Intermediate CA Compromise精选导读

eMudhra Intermediate CA Compromise. This is very, very bad news:

1 分钟69#开发者实时流