“If man chooses oblivion, he can go right on leaving his fate to his political leaders. If he chooses Utopia, he must initiate an enormous education program - immediately, if not sooner.”
-R B Fuiler

  • 1 Post
  • 14 Comments
Joined 12 天前
Cake day: 2025年8月25日
  • nymnympseudonym@piefed.socialtoblueteamsec@infosec.pub•AI-powered ransomware named PromptLock - uses the gpt-oss:20b model from OpenAI locally via the Ollama API to generate malicious Lua scripts on the flyEnglish
    11·
    11 天前

    Perplexity prompt: “quotes from openai about safety testing for gpt-oss”

    Reply below:

    Safety Testing Measures

    • OpenAI’s safety process for open-weight release included technical audits (robustness, bias detection), structured adversarial testing, and evaluation of prompt-injection and jailbreak vulnerabilities.
    • The organization also employed both automated and human review to test for outputs that could cause harm, leveraging cross-disciplinary teams including outside researchers, ethicists, and cybersecurity experts.
    • Feedback from these rounds led to incremental model improvements before the open weights went public.

    Transparency and External Collaboration

    • OpenAI has collaborated with third-party security and ethics researchers to validate its safety protocols and stress-test new models prior to release.
    • The company acknowledges that “Releasing open weights is a significant responsibility due to risks of misuse. We want to be transparent about our process and invite the AI community to help report and address issues that may arise post-release.”
  • nymnympseudonym@piefed.socialtoTech@programming.dev•Study: AI wiping out entry-level jobs for young workersEnglish
    122·
    11 天前

    As a person who has been managing software development teams for 30+ years, I have an observation.
    Invariably, some employees are “average”. Not super geniuses, not workaholics, but people who (say) have been doing a good job with customer support. Generally they can code simple things and know the OS versions we support as a power user – but not as well as a sysadmin.

    I do find that if I tell them to use ChatGPT to help debug issues, they do almost as well as if a sysadmin or more experienced programmer had picked up the ticket. It gets better troubleshooting, they maybe fix an actual root cause bug in our product code.