Nation
World
Politics
Sports
Business
Entertainment
Life
Tech
Science
Opinion
Crime
Health
Oddities

AI poisoning could turn open models into destructive “sleeper agents,” says Anthropic

Por: Ars Technica Tech January 16, 2024

thumbnail

Navigate Filter by topic Settings Front page layout Site theme - Jan 15, 2024 11:02 pm UTC Benj Edwards Getty Images Imagine downloading an open source AI language model, and all seems well at first, but it later turns malicious. On Friday, Anthropic—the maker of competitor —released a about AI sleeper agent large language models (LLMs) that initially seem normal but can deceptively output vulnerable code when given special instructions... + full article



Similar News

Oh, Good, OpenAI’s Biggest Rival Has a Weird Structure Too

Slate USA Tech December 02, 2023

thumbnailThis article is from , a newsletter by Alex Kantrowitz. Life got interesting for Anthropic two weeks ago, when OpenAI nearly lit itself on fire. Anthropic had been operating comfortably in OpenAI’s shadow, collecting billions in investment from Amazon, Google, and others... + más

OpenAI employees revolt after board names new CEO; Altman may head to Microsoft | Ars Technica

Report: After Altman firing, OpenAI tried to merge with rival—and was rejected | Ars Technica


Report: After Altman firing, OpenAI tried to merge with rival—and was rejected

Ars Technica USA Tech November 21, 2023

thumbnailNavigate Filter by topic Settings Front page layout Site theme - Nov 21, 2023 6:03 pm UTC / Anthropic CEO Dario Amodei on Tuesday, July 25, 2023, during a hearing on AI held by the Senate Judiciary Subcommittee on Privacy, Technology, and the Law.Getty Images Bloomberg After... + más

NFL Playoff Scenarios | ABC News

OpenAI board attempts to hit “Ctrl-Z” in talks with Altman to return as CEO | Ars Technica


Amazon to invest as much as $4 billion in ChatGPT rival AI startup

New York Post USA Business September 25, 2023

thumbnailAmazon has plans to invest as much as $4 billion in a generative artificial intelligence startup called Anthropic, which promises to rival ChatGPT, in the e-commerce behemoth’s latest move to get a leg up in the AI space. “As part of the investment, Amazon will take a... + más

Dalvin Cook Posts Photo from 2022 Dolphins Game amid Vikings Release Rumors | Bleacher Report

ChatGPT: Everything You Really Need To Know (In Simple Terms) | Forbes


What to Know About Claude 2, Anthropic's Rival to ChatGPT

Time USA Tech July 19, 2023

thumbnailAnthropic, an AI company, its latest large language model-powered chatbot, Claude 2, last week, the latest development in a race to build bigger and better artificial intelligence models. Claude 2 is an improvement on Anthropic’s previous AI model, Claude 1.3, particularly in... + más

Anthropic introduces Claude, a “more steerable” AI competitor to ChatGPT | Ars Technica

New ChatGPT rival, Claude 2, launches for open beta testing | Ars Technica


AI gains “values” with Anthropic’s new Constitutional AI chatbot approach

Ars Technica USA Tech May 09, 2023

thumbnailNavigate Filter by topic Settings Front page layout Site theme - May 9, 2023 9:16 pm UTC / Anthropic's Constitutional AI logo on a glowing orange background.Anthropic / Benj Edwards On Tuesday, AI startup Anthropic detailed the specific principles of its training approach... + más

Anthropic introduces Claude, a “more steerable” AI competitor to ChatGPT | Ars Technica

Google invests almost $400 million in ChatGPT rival Anthropic | Los Angeles Times


Anthropic introduces Claude, a “more steerable” AI competitor to ChatGPT

Ars Technica USA Tech March 18, 2023

thumbnailNavigate Filter by topic Settings Front page layout Site theme - Mar 17, 2023 9:37 pm UTC Anthropic Share this story On Tuesday, Anthropic Claude, a large language model (LLM) that can generate text, write code, and function as an AI assistant similar to . The model originates... + más

Google invests almost $400 million in ChatGPT rival Anthropic | Los Angeles Times

ChatGPT: Everything You Really Need To Know (In Simple Terms) | Forbes


Google invests almost $400 million in ChatGPT rival Anthropic

Los Angeles Times USA Business February 04, 2023

thumbnailAlphabet’s Google has invested almost $400 million in artificial intelligence startup Anthropic, which is testing a rival to OpenAI’s ChatGPT, according to a person familiar with the deal. Google and Anthropic declined to comment on the investment, but separately announced a... + más

Anthropic introduces Claude, a “more steerable” AI competitor to ChatGPT | Ars Technica

Anthropic, an A.I. Start-Up, Is Said to Be Close to Adding $300 Million | The New York Times



About iurex | Privacy Policy | Disclaimer |