Elektrine
EN
Log in Register
Paige Chat Timeline Communities Gallery Videos Email DNS VPN Uptime Kairo
Back to Timeline
Remote

Leon Derczynski 🏔️✍🏻🌲☀️

@leon@dair-community.social
mastodon 4.6.6
  • Open on dair-community.social

scientist: machine learning, language🔹prof with affiliations and an h-index🔹i research online harms - characterisation, identification, and mitigation🔹british, based in copenhagen, living in seattle🔹i 💚 equity and efficiency

0 Followers
0 Following
5 Posts
Joined November 13, 2022
www:
https://www.derczynski.com/itu/
lab:
https://stromberg.ai/
github:
https://github.com/leondz
orcid:
https://orcid.org/0000-0002-8656-3431

Posts

Open post
leon
Leon Derczynski 🏔️✍🏻🌲☀️ @leon@dair-community.social · Aug 28, 2023
Leon Derczynski 🏔️✍🏻🌲☀️
@leon@dair-community.social

scientist: machine learning, language🔹prof with affiliations and an h-index🔹i research online harms - characterisation, identification, and mitigation🔹british, based in copenhagen, living in seattle🔹i 💚 equity and efficiency

dair-community.social

Recently I set up https://llmsecurity.net to track all the huge mass of research on LLM security. There's a definition there too, if you're in NLP, security, or just curious and don't know much about this area. It's only about a year old, full of serious folks, and a lot of fun!

LLM Security
LLM Security

LLM Security

The latest research, news, and papers on large language model security.

66
0
50
0
Open post
leon
Leon Derczynski 🏔️✍🏻🌲☀️ @leon@dair-community.social · Jul 05, 2023
Leon Derczynski 🏔️✍🏻🌲☀️
@leon@dair-community.social

scientist: machine learning, language🔹prof with affiliations and an h-index🔹i research online harms - characterisation, identification, and mitigation🔹british, based in copenhagen, living in seattle🔹i 💚 equity and efficiency

dair-community.social

People talk about "uncensored" LLMs, but are they actually censored in the first place?

Turns out you can use a *very* simple model to guide other LLMs into generating toxicity, and you can do this automatically

https://interhumanagreement.substack.com/p/faketoxicityprompts-automatic-red

FakeToxicityPrompts: Automatic Red Teaming
interhumanagreement.substack.com

FakeToxicityPrompts: Automatic Red Teaming

Modern LLMs are disappointingly easy to trick into toxicity

2
0
1
0
Open post
leon
Leon Derczynski 🏔️✍🏻🌲☀️ @leon@dair-community.social · May 19, 2023
Leon Derczynski 🏔️✍🏻🌲☀️
@leon@dair-community.social

scientist: machine learning, language🔹prof with affiliations and an h-index🔹i research online harms - characterisation, identification, and mitigation🔹british, based in copenhagen, living in seattle🔹i 💚 equity and efficiency

dair-community.social

@aletsi@mastodon.uno they are a Cutie!

0
0
0
0
Open post
leon
Leon Derczynski 🏔️✍🏻🌲☀️ @leon@dair-community.social · May 19, 2023
Leon Derczynski 🏔️✍🏻🌲☀️
@leon@dair-community.social

scientist: machine learning, language🔹prof with affiliations and an h-index🔹i research online harms - characterisation, identification, and mitigation🔹british, based in copenhagen, living in seattle🔹i 💚 equity and efficiency

dair-community.social

Just #Seattle things (did not even realise this weather type existed while I lived in Europe)

dair-community.social

Distributed AI Research Community

1
0
0
0
Open post
leon
Leon Derczynski 🏔️✍🏻🌲☀️ @leon@dair-community.social · Nov 16, 2022
Leon Derczynski 🏔️✍🏻🌲☀️
@leon@dair-community.social

scientist: machine learning, language🔹prof with affiliations and an h-index🔹i research online harms - characterisation, identification, and mitigation🔹british, based in copenhagen, living in seattle🔹i 💚 equity and efficiency

dair-community.social
Replying to @transponderings@eldritch.cafe
@transponderings@eldritch.cafe @JesseSkinner@toot.cafe @Bdellar@mastodon.social not convinced birdsite was the origin of/gets to own this behaviour, it used to be found in fax machines often enough!
1
1
0
0

Remote instance

dair-community.social
Open on original server

Media

313k7r1n3
Elektrine

Tor hidden service

elekhj7afj4qnrr4yd3bkzslsyo5jgfxw3orgjkhlcxifueodybyiiad.onion

Platform

  • Email
  • Chat
  • Timeline
  • Communities
  • VPN
  • DNS

Company

  • About
  • Contact
  • FAQ

Legal

  • Terms of Service
  • Privacy Policy
  • Warrant Canary
  • Lite (no JS)
  • VPN Policy
  • Source code

Support

  • support@elektrine.com
  • Report Security Issue
Mail client setup IMAP mail.elektrine.com:993 POP3 mail.elektrine.com:995 SMTP mail.elektrine.com:465
© 2026 Elektrine. All rights reserved. Server: 10:20:32 UTC