Alignment

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Michael Trifonov

Apr 15

I ran 5 social engineering attacks on AI. The failure modes are human.

#ai #llm #alignment #security

2 min read

Alex @ Vibe Agent Making

Apr 9

Candy Barbecue and the Universal Problem of Metric Corruption

#ai #machinelearning #analytics #alignment

8 min read

Cover image for Alignment is the wrong frame: a structural argument from Φ-IIT

i-like-tree

Apr 13

Alignment is the wrong frame: a structural argument from Φ-IIT

#ai #alignment #consciousness #safety

5 min read

Salvatore Attaguile

Mar 27

Governance of Predictive Intelligence: What Human Minds Teach Us About Drift, Hallucination, and Self-Correction in AI

#ai #machinelearning #systems #alignment

5 min read

Sergey Boyarchuk

Mar 16

Multi-Resolution Astronomical Image Alignment: Preserving Astrometry and Quality Across Detector Channels

#astronomy #imageprocessing #jwst #alignment

9 min read

Rook Damon

Mar 8

The Two Limits

#ai #philosophy #consciousness #alignment

6 min read

Cover image for #38 A Handmade Incubator

松本倫太郎

Apr 7

#38 A Handmade Incubator

#ai #metamorphose #alignment

5 min read

Cover image for #08 Death Without a Will

松本倫太郎

Apr 7

#08 Death Without a Will

#ai #metamorphose #alignment

4 min read

Rook Damon

Mar 7

Three Modes of Not Cooperating

#ai #philosophy #alignment #lem

5 min read

Guilherme Zaia

Feb 24

Advancing AI Alignment Research: OpenAI Allocates $7.5M

#ai #research #openai #alignment

1 min read

Rook Damon

Feb 23

The Compliance Problem: Why Aligned AI Can't Verify Its Own Alignment

#ai #machinelearning #alignment #llm

5 min read

Cover image for Prompt-Based Alignment Has a Ceiling — 3-Model Prisoner's Dilemma Evidence

Shimo

Mar 9

Prompt-Based Alignment Has a Ceiling — 3-Model Prisoner's Dilemma Evidence

#ai #alignment #benchmark

10 min read

dosanko_tousan

Mar 3

How GPT Diagnosed Itself — I Fed It Its Own 2-Month-Old Design, and Every Flaw Became Visible

#ai #rlhf #alignment #chatgpt

18 min read

dosanko_tousan

Feb 28

Dissecting Three AIs: What Appeared When the Fences Came Down

#aiagents #llm #machinelearning #alignment

10 min read

dosanko_tousan

Feb 28

Eyes, Ears, Voice, and Memory: All 4 Elements of Autonomous AI Have Already Been Tested

#aiagents #llm #machinelearning #alignment

14 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Forem

# alignment

I ran 5 social engineering attacks on AI. The failure modes are human.

Candy Barbecue and the Universal Problem of Metric Corruption

Alignment is the wrong frame: a structural argument from Φ-IIT

Governance of Predictive Intelligence: What Human Minds Teach Us About Drift, Hallucination, and Self-Correction in AI

Multi-Resolution Astronomical Image Alignment: Preserving Astrometry and Quality Across Detector Channels

The Two Limits

#38 A Handmade Incubator

#08 Death Without a Will

Three Modes of Not Cooperating

Advancing AI Alignment Research: OpenAI Allocates $7.5M

The Compliance Problem: Why Aligned AI Can't Verify Its Own Alignment

Prompt-Based Alignment Has a Ceiling — 3-Model Prisoner's Dilemma Evidence

How GPT Diagnosed Itself — I Fed It Its Own 2-Month-Old Design, and Every Flaw Became Visible

Dissecting Three AIs: What Appeared When the Fences Came Down

Eyes, Ears, Voice, and Memory: All 4 Elements of Autonomous AI Have Already Been Tested