Experimental News Clipping Site

Tag: Outputs

  • The Register: Honey, I shrunk the image and now I’m pwned

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/21/google_gemini_image_scaling_attack/ Source: The Register Title: Honey, I shrunk the image and now I’m pwned Feedly Summary: Google’s Gemini-powered tools tripped up by image-scaling prompt injection Security researchers with Trail of Bits have found that Google Gemini CLI and other production AI systems can be deceived by image scaling attacks, a well-known adversarial challenge…

  • Cloud Blog: How startups can help build — and benefit from — the AI revolution

    —

    by

    Kurt Seifried
    in

    Source URL: https://cloud.google.com/blog/products/ai-machine-learning/industry-leaders-on-whats-next-for-startups-and-ai/ Source: Cloud Blog Title: How startups can help build — and benefit from — the AI revolution Feedly Summary: Startups are at the forefront of generative AI development, pushing current capabilities and unlocking new potential. Building on our Future of AI: Perspectives for Startups 2025 report, several of the AI industry leaders…

  • The Register: Don’t want drive-by Ollama attackers snooping on your local chats? Patch now

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/19/ollama_driveby_attack/ Source: The Register Title: Don’t want drive-by Ollama attackers snooping on your local chats? Patch now Feedly Summary: Reconfigure local app settings via a ‘simple’ POST request A now-patched flaw in popular AI model runner Ollama allows drive-by attacks in which a miscreant uses a malicious website to remotely target people’s personal…

  • Tomasz Tunguz: When One AI Grades Another’s Work

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.tomtunguz.com/evolution-of-ai-judges-improving-evoblog/ Source: Tomasz Tunguz Title: When One AI Grades Another’s Work Feedly Summary: Since launching EvoBlog internally, I’ve wanted to improve it. One way of doing this is having an LLM judge the best posts rather than a static scoring system. I appointed Gemini 2.5 to be that judge. This post is a…

  • Simon Willison’s Weblog: TIL: Running a gpt-oss eval suite against LM Studio on a Mac

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Aug/17/gpt-oss-eval-suite/#atom-everything Source: Simon Willison’s Weblog Title: TIL: Running a gpt-oss eval suite against LM Studio on a Mac Feedly Summary: TIL: Running a gpt-oss eval suite against LM Studio on a Mac The other day I learned that OpenAI published a set of evals as part of their gpt-oss model release, described in…

  • Embrace The Red: Amp Code: Invisible Prompt Injection Fixed by Sourcegraph

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/amp-code-fixed-invisible-prompt-injection/ Source: Embrace The Red Title: Amp Code: Invisible Prompt Injection Fixed by Sourcegraph Feedly Summary: In this post we will look at Amp, a coding agent from Sourcegraph. The other day we discussed how invisible instructions impact Google Jules. Turns out that many client applications are vulnerable to these kinds of attacks…

  • The Register: Little LLM on the RAM: Google’s Gemma 270M hits the scene

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/15/little_llm_on_the_ram/ Source: The Register Title: Little LLM on the RAM: Google’s Gemma 270M hits the scene Feedly Summary: A tiny model trained on trillions of tokens, ready for specialized tasks Google has unveiled a pint-sized new addition to its “open" large language model lineup: Gemma 3 270M.… AI Summary and Description: Yes Summary:…

  • Wired: OpenAI Designed GPT-5 to Be Safer. It Still Outputs Gay Slurs

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.wired.com/story/openai-gpt5-safety/ Source: Wired Title: OpenAI Designed GPT-5 to Be Safer. It Still Outputs Gay Slurs Feedly Summary: The new version of ChatGPT explains why it won’t generate rule-breaking outputs. WIRED’s initial analysis found that some guardrails were easy to circumvent. AI Summary and Description: Yes Summary: The text discusses a new version of…