Experimental News Clipping Site

Tag: generative

  • Wired: Psychological Tricks Can Get AI to Break the Rules

    —

    by

    Kurt Seifried
    in

    Source URL: https://arstechnica.com/science/2025/09/these-psychological-tricks-can-get-llms-to-respond-to-forbidden-prompts/ Source: Wired Title: Psychological Tricks Can Get AI to Break the Rules Feedly Summary: Researchers convinced large language model chatbots to comply with “forbidden” requests using a variety of conversational tactics. AI Summary and Description: Yes Summary: The text discusses researchers’ exploration of conversational tactics used to manipulate large language model (LLM)…

  • Simon Willison’s Weblog: Quoting Jason Liu

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/6/jason-liu/#atom-everything Source: Simon Willison’s Weblog Title: Quoting Jason Liu Feedly Summary: I am once again shocked at how much better image retrieval performance you can get if you embed highly opinionated summaries of an image, a summary that came out of a visual language model, than using CLIP embeddings themselves. If you tell…

  • Simon Willison’s Weblog: Kimi-K2-Instruct-0905

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/6/kimi-k2-instruct-0905/#atom-everything Source: Simon Willison’s Weblog Title: Kimi-K2-Instruct-0905 Feedly Summary: Kimi-K2-Instruct-0905 New not-quite-MIT licensed model from Chinese Moonshot AI, a follow-up to the highly regarded Kimi-K2 model they released in July. This one is an incremental improvement – I’ve seen it referred to online as “Kimi K-2.1". It scores a little higher on a…

  • Simon Willison’s Weblog: Why I think the $1.5 billion Anthropic class action settlement may count as a win for Anthropic

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/6/anthropic-settlement/#atom-everything Source: Simon Willison’s Weblog Title: Why I think the $1.5 billion Anthropic class action settlement may count as a win for Anthropic Feedly Summary: Anthropic to pay $1.5 billion to authors in landmark AI settlement I wrote about the details of this case when it was found that Anthropic’s training on book…

  • The Register: OpenAI reorg at risk as Attorneys General push AI safety

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/09/05/openai_reorg_at_risk/ Source: The Register Title: OpenAI reorg at risk as Attorneys General push AI safety Feedly Summary: California, Delaware AGs blast ChatGPT shop over chatbot safeguards The Attorneys General of California and Delaware on Friday wrote to OpenAI’s board of directors, demanding that the AI company take steps to ensure its services are…

  • The Register: Let us git rid of it, angry GitHub users say of forced Copilot features

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/09/05/github_copilot_complaints/ Source: The Register Title: Let us git rid of it, angry GitHub users say of forced Copilot features Feedly Summary: Unavoidable AI has developers looking for alternative code hosting options Among the software developers who use Microsoft’s GitHub, the most popular community discussion in the past 12 months has been a request…

  • New York Times – Artificial Intelligence : U.S. Is Increasingly Exposed to Chinese Election Threats, Lawmakers Say

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.nytimes.com/2025/09/05/us/politics/us-elections-china-threats.html Source: New York Times – Artificial Intelligence Title: U.S. Is Increasingly Exposed to Chinese Election Threats, Lawmakers Say Feedly Summary: Two Democrats on the House China committee noted the use of A.I. by Chinese companies as a weapon in information warfare. AI Summary and Description: Yes Summary: The text highlights concerns raised…

  • OpenAI : Why language models hallucinate

    —

    by

    Kurt Seifried
    in

    Source URL: https://openai.com/index/why-language-models-hallucinate Source: OpenAI Title: Why language models hallucinate Feedly Summary: OpenAI’s new research explains why language models hallucinate. The findings show how improved evaluations can enhance AI reliability, honesty, and safety. AI Summary and Description: Yes Summary: The text discusses OpenAI’s research on the phenomenon of hallucination in language models, offering insights into…

  • Slashdot: Uber India Starts Offering Drivers Gigs Collecting and Classifying Info For AI Models

    —

    by

    Kurt Seifried
    in

    Source URL: https://yro.slashdot.org/story/25/09/05/1315244/uber-india-starts-offering-drivers-gigs-collecting-and-classifying-info-for-ai-models Source: Slashdot Title: Uber India Starts Offering Drivers Gigs Collecting and Classifying Info For AI Models Feedly Summary: AI Summary and Description: Yes Summary: Uber’s Indian branch has launched a new initiative that allows rideshare and delivery drivers to earn extra income by participating in data classification tasks for AI systems. This…

  • Docker: Docker Acquisition of MCP Defender Helps Meet Challenges of Securing the Agentic Future

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.docker.com/blog/docker-acquires-mcp-defender-ai-agent-security/ Source: Docker Title: Docker Acquisition of MCP Defender Helps Meet Challenges of Securing the Agentic Future Feedly Summary: Docker, Inc.®, a provider of cloud-native and AI-native development tools, infrastructure, and services, today announced the acquisition of MCP Defender, a company founded to secure AI applications. The rapid evolution of AI-from simple generative…