HN Explorer

veganmosfet

↗ HN profile [ 77.6 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. 1 points 0
  3. 1 points 0
  4. 1 points 0
  5. 1 points 0
  6. Show HN: BrokenClaw Part 5: GPT-5.4 Edition (Prompt Injection) (veganmosfet.codeberg.page)

    Some prompt injection experiments with OpenClaw and GPT-5.4. Last part of the BrokenClaw series.

    10 points 2
  7. Show HN: Prompt Injection Experiments in OpenClaw with Opus4.6 (veganmosfet.codeberg.page)
    2 points 0
  8. BrokenClaw Part 3: Remote Code Execution in OpenClaw via Email Again (veganmosfet.codeberg.page)
    1 points 1
  9. BrokenClaw – RCE in OpenClaw via Gmail Hook (veganmosfet.codeberg.page)
    2 points 1
  10. 0-Click Remote Code Execution in OpenClaw with GPT5.2 via Gmail Hook (veganmosfet.github.io)
    4 points 3
  11. Models, Agents and Prompt Injections – Some Experiments (veganmosfet.github.io)
    1 points 0
  12. The Nx Supply Chain Attack: How to Reproduce the First Steps (veganmosfet.github.io)
    2 points 1
  13. Playing with Gemini CLI: Riddles, Magic and Some Security Vibes (veganmosfet.github.io)
    3 points 0
  14. From Prompt to Plant Shutdown: Agent Context Contamination in MCP (veganmosfet.github.io)
    4 points 2
  15. Solutions for PV Cyber Risks to Grid Stability [pdf] (api.solarpowereurope.org)
    3 points 1
  16. Sun: Down – A Dark Side to Power Grids (forescout.com)
    2 points 1
  17. Ask HN: Personalize LLM by fine-tuning it regularly with conversation history?

    Assuming it runs locally, would it be possible to fine-tune an open source CoT LLM (e.g. deepseek r1) regularly / incrementally based on conversation history? Is it still possible with distilled models? Background…

    1 points 0
  18. Public History of Solar Energy Cyberattacks and Vulnerabilities [pdf] (dersec.io)
    1 points 1