x

LESSWRONG
LW

Seon Gunness

Seon Gunness

Message

11

2

1

3y

Seon Gunness

11

3y

Seon Gunness — LessWrong

On open-science research labs on discord, and getting more people.

Note that the audio doesn't follow the post verbatim;it's still essentially the same content though. (audio version below) TL;DR- There's a bunch of groups of glorified science labs on mostly discord doing mostly AI research, you should join them 1 Definitions This is not about: Open access - The concept...

Jul 11, 2025•10

Visual Prompt Injections: Results on testing AI spam-defense and AI vulnerability to deceptive web ads.

Epistemic Status: Exploratory/my best guess https://www.lesswrong.com/posts/Hrm59GdN2yDPWbtrd/feature-idea-epistemic-status Epistemic Effort: ~ 2 months of work Contributions: Thanks to Clement Neo and Alignment Jams / Apart Research! Summary/abstract:Split into 3 parts: 1:Determine the smallest text size at which models begin misreading on-screen content. 2:Evaluated defensive visual prompt injections against AI-generated spam by incorporating...

Jun 3, 2025•4