Elektrine lite

← Feed

Florencio Cano

florenciocano@infosec.exchange

<p>Principal Product Security Engineer</p>

Posts

  • Post #4430513

    The book &quot;The Goal&quot; is a great read to understand where to use AI to really improve performance. If you improve/automate the wrong step the result is worse.

  • Post #4060447

    Gemma 4 31B quantized is hands down the best model I have been able to run locally on a RTX 4090. I run it with `llama.cpp/build/bin/llama-server -m ~/models/gemma-4-31B-it-Q4_K_M.gguf -c 65536 -ngl 99 -ctk q4_0 -ctv q4_0 -fa on --host 0.0.0.0 --port 8081` Any suggestion to run it more efficiently? Any other model I should try?

  • Post #4015884

    HackMyClaw was an OpenClaw prompt injection challenge: make Fiu leak secrets through email. After many attempts, no one succeeded https://hackmyclaw.com/

  • Post #3928562

    RE: https://infosec.exchange/@SteveBellovin/116944300269431503 &quot;one of the proof’s implications is that there will always be a way to prompt an AI system to disregard its rules — it’s just a matter of finding it.&quot;

  • Post #3904393

    Related to the #HuggingFace breach https://huggingface.co/blog/security-incident-july-2026, I want highlight this paragraph: &quot;The intrusion started where AI platforms are uniquely exposed: the data-processing pipeline. A malicious dataset abused two code-execution paths in our dataset processing (a remote-code dataset loader and a template-injection in a dataset configuration) to run code on a processing worker.&quot; It&#39;s an example that a malicious or especially crafted database can...

  • Post #1745762

    Is anyone running #openclaw with a local LLM and it is working well? I&amp;#39;m specially interested in LLMs that can be run in GPUs with 24GB vRAM.

  • Post #1745757

    Agent Skills: Explore security threats and controls https://developers.redhat.com/articles/2026/03/10/agent-skills-explore-security-threats-and-controls