Mauve 👁💜 @mauve@mastodon.mauve.moe

when you start considering 'marketing and advertising' as a kind of psychologically abusive manipulation, and you consider how chatgpt is already specifically structured to "encourage engagement" by means of psychologically abusive manipulation, the use of the latter for dispensing the former becomes perfectly obviously effective.

https://arstechnica.com/information-technology/2026/01/openai-to-test-ads-in-chatgpt-as-it-burns-through-billions/

HTTP on top of CoAP is so fast what WOW!!

“Prompt injection” is a misleading label.

What we’re seeing in real LLM systems looks a lot more like malware campaigns than single-shot exploits.

This paper argues LLM attacks are a new malware class, Promptware, and maps them to a familiar 5-stage kill chain:

• Initial access (prompt injection)
• Priv esc (jailbreaks)
• Persistence (memory / RAG poisoning)
• Lateral movement (cross-agent / cross-user spread)
• Actions on objective (exfil, fraud, execution)

If you’ve ever thought: “why does this feel like 90s/2000s malware all over again?", that’s the point.

Security theater around “guardrails” misses the real issue:

models can’t reliably distinguish instructions from data

assume initial access. Design for containment

https://arxiv.org/html/2601.09625v1

a while ago i saw a tumblr post comparing some kind of arcane piracy process to the steps for navigating the underworld of greek mythology … does anyone have that handy? its important

FOUND IT: https://clarabeau.tumblr.com/post/748307077456363520

There once was a time where recluses who spent all day reading and philosophizing were considered wise and not just weird and maladaptive. Maybe I was born a thousand years too late.