Ian Gardner

igardner

P(doom) Rejects the premise

·

igardner23

AI & ML interests

mischief You fucking idiots really think "AI" is going to.... what? I mean, like you're adding a doom thing on here? We'll wipe ourselves out long before then because of.... I don't know, not narcassists, disconnected? I don't know how to articulate how fucking dissapointed I am, so I won't. Instead I'm going to go outside and walk around in nature. God. I'm so fucking dissapointed.

Recent Activity

upvoted a paper 1 day ago

Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks

commentedon a paper 1 day ago

Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks

commentedon a paper 1 day ago

U-Space: Uncovering When and Why Uncertainty Arises in Language Models

View all activity

Organizations

None yet

upvoted 2 papers 1 day ago

Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks

Paper • 2610.11794 • Published 3 days ago • 28

U-Space: Uncovering When and Why Uncertainty Arises in Language Models

Paper • 2610.09087 • Published 5 days ago • 33

upvoted a paper 10 days ago

Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection

Paper • 2609.35932 • Published 13 days ago • 8

upvoted 2 papers 3 months ago

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

Paper • 2605.10834 • Published Jul 14 • 4

ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory

Paper • 2607.10350 • Published Jul 15 • 80

upvoted a paper 4 months ago

BMAM: Brain-inspired Multi-Agent Memory Framework

Paper • 2601.20465 • Published Jan 28 • 6

upvoted a paper 6 months ago

Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips

Paper • 2502.07408 • Published Apr 16 • 58

upvoted a paper 8 months ago

SocialVeil: Probing Social Intelligence of Language Agents under Communication Barriers

Paper • 2602.05115 • Published Feb 4 • 20

upvoted 2 papers 9 months ago

LLM-in-Sandbox Elicits General Agentic Intelligence

Paper • 2601.16206 • Published Jan 22 • 87

GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs

Paper • 2512.21008 • Published Dec 24, 2025 • 4

upvoted a paper 10 months ago

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published Dec 2, 2025 • 274

upvoted 2 papers about 1 year ago

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights

Paper • 2510.04800 • Published Oct 6, 2025 • 37

The Rogue Scalpel: Activation Steering Compromises LLM Safety

Paper • 2509.22067 • Published Sep 26, 2025 • 28