Mauve 👁💜 @mauve@mastodon.mauve.moe
- Pronouns
- they/them/it
- mauve+fedi@mauve.moe
- Matrix
- @mauve:mauve.moe
- Github/Gitlab/Discord
- @RangerMauve
Mod
Occult cyberpunk. Yap with me about decentralized systems, wearable computing, and biohacking.
Joined Apr 2022
Mauve 👁💜
boosted
morse code is fucked up bc you'll be walking around mindin your own business when a bird suddenly goes
h
Mauve 👁💜
boosted
I love "the field guide to understanding human error"
Any book or blog recommendations for learning about others' failures and what to learn from them?
Mauve 👁💜
boosted
"The competent cyber warrior learns from their mistakes. The cyber master learns from the mistakes of others." - The Art of Cyber War
Arch linux uses me BTW
TIL about https://www.picmix.com/ for making collages out of gifs
Microanthropology
Had more mixed success with meatspace human interaction today. I think next time I should aim to ve in the same place for multiple days and revisit people to build rapport over time.
Wish my TTS for listening to books would speak the punctuation so I could understand wtf this code actually looks like.
New moon tomorrow. Set some time aside before bed to ground yourself for the upcoming cycle.
Mauve 👁💜
boosted
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.
Managed to rig my borderlands 3 character to have zero shields and 1HP at level 60. Constant death.
Mauve 👁💜
boosted
Really appreciate being able to chill at home today with all this snow out. 💜
Thwy should just turn G-Mail into a PDS
Mauve 👁💜
boosted
“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
Adobe is an avsolute scumbag of a company and the corporate world enabling their predatory behavior makes me sick.
Damn I really need to paint rn but I gotta wait another day or two 🥲
- Pronouns
- they/them/it
- mauve+fedi@mauve.moe
- Matrix
- @mauve:mauve.moe
- Github/Gitlab/Discord
- @RangerMauve
Mod
Occult cyberpunk. Yap with me about decentralized systems, wearable computing, and biohacking.
Joined Apr 2022
