GoKawiil - Latest Tech News & Aggregated Headlines

How to stop AI agents going rogue

feeds.bbci.co.uk Unknown 2025-10-31 07:59:49

How to stop AI agents going rogue 1 hour ago Share Save Sean McManus Technology Reporter Share Save Getty Images Anthropic tested a range of leading AI models for potential risky behaviour Disturbing results emerged earlier this year, when AI developer Anthropic tested leading AI models to see if they engaged in risky behaviour when using sensitive information. Anthropic's own AI, Claude, was among those tested. When given access to an email account it discovered that a company executive was

Topics: agent agents ai information security

Shop Amazon

How to Fix Your Context

news.ycombinator.com Drew Breunig 2025-11-02 08:09:53

Mitigating & Avoiding Context Failures Following up on our earlier post, “How Long Contexts Fail”, let’s run through the ways we can mitigate or avoid these failures entirely. But before we do, let’s briefly recap some of the ways long contexts can fail: Context Poisoning: When a hallucination or other error makes it into the context, where it is repeatedly referenced. When a hallucination or other error makes it into the context, where it is repeatedly referenced. Context Distraction: When

Topics: agent context information tool tools

Shop Amazon

How to build a coding agent

news.ycombinator.com Geoffrey Huntley 2025-11-02 03:21:14

😎 The following was developed last month and has already been delivered at two conferences. If you would like for me to run a workshop similar to this at your employer, please get in contact Hey everyone, I'm here today to teach you how to build a coding agent. By this stage of the conference, you may be tired of hearing the word "agent". You hear the word frequently. However, it appears that everyone is using this term loosely without a clear understanding of what it means or how these coding

Topics: agent claude file riddle tool

Shop Amazon

Show HN: How to Build a Coding Agent (free workshop)

news.ycombinator.com Geoffrey Huntley 2025-11-02 09:21:14

😎 The following was developed last month and has already been delivered at two conferences. If you would like for me to run a workshop similar to this at your employer, please get in contact Hey everyone, I'm here today to teach you how to build a coding agent. By this stage of the conference, you may be tired of hearing the word "agent". You hear the word frequently. However, it appears that everyone is using this term loosely without a clear understanding of what it means or how these coding

Topics: agent claude file riddle tool

Shop Amazon

Websites and web developers mostly don't care about client-side problems

news.ycombinator.com Unknown 2025-11-02 01:09:11

You're using a tool with a too-generic User-Agent You're probably reading this page because you've attempted to access some part of my blog (Wandering Thoughts) or CSpace, the wiki thing it's part of. Unfortunately whatever you're using to do so has a HTTP User-Agent header value that is too generic or otherwise excessively suspicious. Unfortunately, as of early 2025 there's a plague of high volume crawlers (apparently in part to gather data for LLM training) that behave like this. To reduce th

Topics: agent generic http user using

Shop Amazon

My tips for using LLM agents to create software

news.ycombinator.com Some Random Dude On The Internet 2025-11-02 06:59:02

This post details my experiences creating software with LLM coding agents, emphasizing that what you do with AI agents is ‘creation’, not just 'coding,' and sharing what worked for me. This is not 'The One True Path To AI Success.' tl;dr: I’m not a professional developer, just a hobbyist with aspirations I wanted to accomplish a coding project beyond my skill level and have been experimenting with agentic coding tools for several months (spoiler: mostly success) You should use Anthropic’

Topics: agent context file like test

Shop Amazon

OpenCUA’s open source computer-use agents rival proprietary models from OpenAI and Anthropic

venturebeat.com Ben Dickson 2025-11-02 11:25:35

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now A new framework from researchers at The University of Hong Kong (HKU) and collaborating institutions provides an open source foundation for creating robust AI agents that can operate computers. The framework, called OpenCUA, includes the tools, data, and recipes for scaling the development of computer-use agents (CUAs). Models trained usin

Topics: agents data models opencua source

Shop Amazon

Launch HN: Inconvo (YC S23) – AI agents for customer-facing analytics

news.ycombinator.com Unknown 2025-11-04 10:59:07

Hi HN, we are Liam and Eoghan of Inconvo ( https://inconvo.com ), a platform that makes it easy to build and deploy AI analytics agents into your SaaS products, so your customers can quickly interact with their data. There’s a demo video at https://www.youtube.com/watch?v=4wlZL3XGWTQ and a live demo at https://demo.inconvo.ai/ (no signup required). Docs are at https://inconvo.com/docs. SaaS products typically offer dashboards and reports, which work for high-level metrics but are clunky for dr

Topics: agent ai analytics https inconvo

Shop Amazon

Meet the researcher hosting a scientific conference by and for AI

technologyreview.com Peter Hall 2025-11-05 03:00:00

That idea is not without its detractors. Among other issues, many feel AI is not capable of the creative thought needed in research, makes too many mistakes and hallucinations, and may limit opportunities for young researchers. Nevertheless, a number of scientists and policymakers are very keen on the promise of AI scientists. The US government’s AI Action Plan describes the need to “invest in automated cloud-enabled labs for a range of scientific fields.” Some researchers think AI scientists c

Topics: agents ai lab scientists work

Shop Amazon

Show HN: I replaced vector databases with Git for AI memory (PoC)

news.ycombinator.com Unknown 2025-11-07 22:20:11

DiffMem: Git-Based Differential Memory for AI Agents DiffMem is a lightweight, git-based memory backend designed for AI agents and conversational systems. It uses Markdown files for human-readable storage, Git for tracking temporal evolution through differentials, and an in-memory BM25 index for fast, explainable retrieval. This project is a proof-of-concept (PoC) exploring how version control systems can serve as a foundation for efficient, scalable memory in AI applications. At its core, Dif

Topics: agents ai diffmem git memory

Shop Amazon

Sequoia backs Zed

news.ycombinator.com Unknown 2025-11-08 00:13:16

Nathan Sobo August 20th, 2025 Today we're announcing our $32M Series B led by Sequoia Capital with participation from our existing investors, bringing our total funding to over $42M. For the past four years, we've been building the world's fastest IDE, but that's just the foundation for what comes next. Our ultimate vision is a new way to collaborate on software, where conversations about code remain connected to the code itself, instead of being tied to aging snapshots or scattered across dif

Topics: agents ai code commits just

Shop Amazon

Device searches at the US border hit record high, new data shows

techcrunch.com Zack Whittaker 2025-11-08 21:29:01

In Brief U.S. border agents searched more electronic devices during a three-month period than ever before, according to new government statistics. The data shows that U.S. Customs and Border Protection, the agency tasked with immigration screening at the U.S. border, searched 14,899 devices of international travelers between April through June, a 17% rise on the previous record high recorded in early 2022. Most of these searches are “basic,” where U.S. border agents demand the password to the

Topics: agents border country device devices

Shop Amazon

Do Large Language Models Dream of AI Agents?

wired.com Will Knight 2025-11-09 02:00:00

During sleep, the human brain sorts through different memories, consolidating important ones while discarding those that don’t matter. What if AI could do the same? Bilt, a company that offers local shopping and restaurant deals to renters, recently deployed several million agents with the hopes of doing just that. Bilt uses technology from a startup called Letta that allows agents to learn from previous conversations and share memories with one another. Using a process called “sleeptime compu

Topics: agents ai context information memory

Shop Amazon

Perplexity’s Comet AI browser tricked into buying fake items online

bleepingcomputer.com Unknown 2025-11-09 05:31:13

A study looking into agentic AI browsers has found that these emerging tools are vulnerable to both new and old schemes that could make them interact with malicious pages and prompts. Agentic AI browsers can autonomously browse, shop, and manage various online tasks (like handling email, booking tickets, filing forms, or controlling accounts). Perplexity’s Comet is currently the primary example of agentic AI browsers. Microsoft Edge is also embedding agentic browsing features through a Copilot

Topics: agentic ai comet fake guardio

Shop Amazon

Sequoia Backs Zed's Vision for Collaborative Coding

news.ycombinator.com Unknown 2025-11-09 12:13:16

Nathan Sobo August 20th, 2025 Today we're announcing our $32M Series B led by Sequoia Capital with participation from our existing investors, bringing our total funding to over $42M. For the past four years, we've been building the world's fastest IDE, but that's just the foundation for what comes next. Our ultimate vision is a new way to collaborate on software, where conversations about code remain connected to the code itself, instead of being tied to aging snapshots or scattered across dif

Topics: agents ai code commits just

Shop Amazon

Tidewave Web: in-browser coding agent for Rails and Phoenix

news.ycombinator.com Unknown 2025-11-10 15:43:04

Today, we’re introducing Tidewave Web for Rails and Phoenix: a coding agent that runs directly in the browser alongside your web application, in your own development environment, with full page and code context. Unlike traditional coding agents that require constant back-and-forth, Tidewave Web knows your UI state, understands your framework, and runs within your actual development environment. No more describing what’s on your screen, copying stacktraces, or losing context between tools. Our

Topics: agent browser tidewave tools web

Shop Amazon

Databricks is raising a Series K Investment at >$100B valuation

news.ycombinator.com Unknown 2025-11-10 17:06:15

SAN FRANCISCO, CA — August 19, 2025 — Databricks, the Data and AI company, today announced it has signed a term sheet for its Series K round, which it expects to close soon with backing from existing investors. This funding values the company at >$100 billion. The company expects to use the new capital to accelerate its AI strategy — expanding Agent Bricks, investing in its new database offering Lakebase, and fueling global growth. At the June Data + AI Summit, Databricks introduced a new produ

Topics: agents ai company data databricks

Shop Amazon

Grammarly Pushes Beyond Proofreading With AI-Powered Writing Guidance

cnet.com See Full Bio 2025-11-11 00:45:04

Grammarly is expanding beyond its grammar-checking roots. The company has announced the launch of several specialized AI "agents" and a new writing tool called Grammarly Docs, designed to help students and professionals with everything from drafting essays to polishing workplace emails. It's another example of generative AI expanding beyond general-purpose chatbots like ChatGPT and Gemini into more specialized domains. Other examples of gen AI in educational circles include Google's NotebookLM

Topics: agents ai company grammarly writing

Shop Amazon

Alation says new query feature offers 30% accuracy boost, helping enterprises turn data catalogs into problem solvers

venturebeat.com Sean Michael Kerner 2025-11-11 05:43:19

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now The enterprise data catalog market has undergone dramatic shifts in the modern gen AI era. Traditional data catalogs served as static repositories where users searched for datasets and documentation. The market expanded to include data governance capabilities with many vendors branding the technology as data intelligence platforms. Early

Topics: agents ai alation data intelligence

Shop Amazon

VB AI Impact Series: Can you really govern multi-agent AI?

venturebeat.com Vb Staff 2025-11-12 15:50:00

Single copilots are yesterday’s news. Competitive differentiation is all about launching a network of specialized agents that collaborate, self-critique, and call the right model for every step. The latest installment of VentureBeat’s AI Impact Series, presented by SAP in San Francisco, tackled the issue of deploying and governing multi-agent AI systems. Yaad Oren, managing director SAP Labs U.S. and global head of research & innovation at SAP, and Raj Jampa, SVP and CIO with Agilent, an analyt

Topics: agents ai data layer sap

Shop Amazon

AI Is About to Radically Alter Military Command Structures That Date Back to Napoleon

gizmodo.com Benjamin Jensen 2025-11-15 02:30:45

Benjamin Jensen, Professor of Strategic Studies at the Marine Corps University School of Advanced Warfighting; Scholar-in-Residence, American University School of International Service This article is republished from The Conversation under a Creative Commons license. Read the original article. Despite two centuries of evolution, the structure of a modern military staff would be recognizable to Napoleon. At the same time, military organizations have struggled to incorporate new technologies as

Topics: agents ai command military staff

Shop Amazon

Grammarly says its AI agent can predict an A paper

theverge.com Jess Weatherbed 2025-11-15 10:00:00

Posts from this author will be added to your daily email digest and your homepage feed. Grammarly is launching several new AI agents for specific writing challenges, from educators trying to detect plagiarism and AI-generated text to students looking to gauge reader reaction to their paper, needing help with citations, and even seeing their predicted grade. The specialized AI agents are available in docs — which is Grammarly’s new “AI-native writing surface,” according to the company’s press re

Topics: agent ai grammarly students writing

Shop Amazon

Grammarly's new AI agents can detect AI text and find citations for you - automatically

zdnet.com Webb Wright 2025-11-15 16:00:18

Catherine Falls Commercial/Moment via Getty Images ZDNET's key takeaways Grammarly's new AI agents are designed to provide assistance without prompting. They're geared toward students and professional development. Grammarly says agents will become a major focus for the company. Get more in-depth ZDNET tech coverage: Add us as a preferred Google source on Chrome and Chromium browsers. Professional writers have long relied on literary agents to help with the publication and sale of their wor

Topics: agent agents ai grammarly new

Shop Amazon

LLMs and coding agents are a security nightmare

news.ycombinator.com Gary Marcus 2025-11-15 20:04:34

Last October, I wrote an essay called “When it comes to security, LLMs are like Swiss cheese — and that’s going to cause huge problems” warning that “The more people use LLMs, the more trouble we are going to be in”. Until last week, when I went to Black Hat Las Vegas, I had no earthly idea how serious the problems were. There, I got to know Nathan Hamiel, a Senior Director of Research at Kudelski Security and the AI, ML, and Data Science track lead for Black Hat, and also sat in on a talk by tw

Topics: agents code coding llm malicious

Shop Amazon

LLMs and Coding Agents = Security Nightmare

news.ycombinator.com Gary Marcus 2025-11-16 08:04:34

Last October, I wrote an essay called “When it comes to security, LLMs are like Swiss cheese — and that’s going to cause huge problems” warning that “The more people use LLMs, the more trouble we are going to be in”. Until last week, when I went to Black Hat Las Vegas, I had no earthly idea how serious the problems were. There, I got to know Nathan Hamiel, a Senior Director of Research at Kudelski Security and the AI, ML, and Data Science track lead for Black Hat, and also sat in on a talk by tw

Topics: agents code coding llm malicious

Shop Amazon

ICE Agents Accidentally Add Random Person to Group Chat, Uncover Highly Sensitive Data

futurism.com Unknown 2025-11-15 22:30:42

"I saw the rap sheet and license plate numbers and was like WTAF." Mass Text US Immigration and Customs Enforcement (ICE) agents accidentally added a random person to a mass group text in which officers from multiple federal law enforcement agencies discussed extremely sensitive information about arrests, targets, and strategy. As 404 Media reports, the group text was titled "Mass Text" and included an unredacted ICE document titled "Field Operations Worksheet." The document included "detaile

Topics: agents chat enforcement ice law

Shop Amazon

OpenAI prepares Chromium-based AI browser to take on Google

bleepingcomputer.com Unknown 2025-11-15 16:23:03

OpenAI is testing an AI-powered browser that uses Chromium as its underlying engine, and it could debut on macOS first. My sources tell me that OpenAI has already started updating ChatGPT to power the Chrome rival. OpenAI is building an AI-powered tab selection, a new tab page, and a feature that allows the browser to do the browsing for you. It could be similar to Copilot mode in Edge. OpenAI already has Agent mode in ChatGPT. For those unaware, Agent mode in ChatGPT is powered by a Linux t

Topics: agent browser chatgpt mode openai

Shop Amazon

Best Practices for Building Agentic AI Systems

news.ycombinator.com Unknown 2025-11-15 17:39:34

I’ve been experimenting with adding AI agents to UserJot, our feedback, roadmap, and changelog platform. Not the simple “one prompt, one response” stuff. Real agent systems where multiple specialized agents communicate, delegate tasks, and somehow don’t crash into each other. The goal was to analyze customer feedback at scale. Find patterns across hundreds of posts. Auto-generate changelog entries. Things that were basically impossible to do manually. I spent weeks reverse engineering tools lik

Topics: agent agents feedback subagent tasks

Shop Amazon

Launch HN: Embedder (YC S25) – Claude code for embedded software

news.ycombinator.com Unknown 2025-11-16 12:38:05

Hey HN - We’re Bob and Ethan from Embedder ( https://embedder.dev ), a hardware-aware AI coding agent that can write firmware and test it on physical hardware. Here’s a demo in which we integrate a magnetometer for the Pebble 2 smartwatch: https://www.youtube.com/watch?v=WOpAfeiFQkQ We were frustrated by the gap between coding agents and the realities of writing firmware. We'd ask Cursor to, say, write an I2C driver for a new sensor on an STM32, and it would confidently spit out code that used

Topics: agent coding context embedder hardware

Shop Amazon

Launch HN: Embedder (YC S25) – Claude Code for Embedded Software

news.ycombinator.com Unknown 2025-11-17 00:38:05

Hey HN - We’re Bob and Ethan from Embedder ( https://embedder.dev ), a hardware-aware AI coding agent that can write firmware and test it on physical hardware. Here’s a demo in which we integrate a magnetometer for the Pebble 2 smartwatch: https://www.youtube.com/watch?v=WOpAfeiFQkQ We were frustrated by the gap between coding agents and the realities of writing firmware. We'd ask Cursor to, say, write an I2C driver for a new sensor on an STM32, and it would confidently spit out code that used

Topics: agent coding context embedder hardware

Shop Amazon

Latest Tech News

How to stop AI agents going rogue

How to Fix Your Context

How to build a coding agent

Show HN: How to Build a Coding Agent (free workshop)

Websites and web developers mostly don't care about client-side problems

My tips for using LLM agents to create software

OpenCUA’s open source computer-use agents rival proprietary models from OpenAI and Anthropic

Launch HN: Inconvo (YC S23) – AI agents for customer-facing analytics

Meet the researcher hosting a scientific conference by and for AI

Show HN: I replaced vector databases with Git for AI memory (PoC)

Sequoia backs Zed

Device searches at the US border hit record high, new data shows

Do Large Language Models Dream of AI Agents?

Perplexity’s Comet AI browser tricked into buying fake items online

Sequoia Backs Zed's Vision for Collaborative Coding

Tidewave Web: in-browser coding agent for Rails and Phoenix

Databricks is raising a Series K Investment at >$100B valuation

Grammarly Pushes Beyond Proofreading With AI-Powered Writing Guidance

Alation says new query feature offers 30% accuracy boost, helping enterprises turn data catalogs into problem solvers

VB AI Impact Series: Can you really govern multi-agent AI?

AI Is About to Radically Alter Military Command Structures That Date Back to Napoleon

Grammarly says its AI agent can predict an A paper

Grammarly's new AI agents can detect AI text and find citations for you - automatically

LLMs and coding agents are a security nightmare

LLMs and Coding Agents = Security Nightmare

ICE Agents Accidentally Add Random Person to Group Chat, Uncover Highly Sensitive Data

OpenAI prepares Chromium-based AI browser to take on Google

Best Practices for Building Agentic AI Systems

Launch HN: Embedder (YC S25) – Claude code for embedded software

Launch HN: Embedder (YC S25) – Claude Code for Embedded Software

About GoKawiil

Privacy

Advertising

Latest Tech News

Trending Topics

Hot Now

Popular

Emerging

About GoKawiil

Privacy

Advertising