RSS

Strad Slater

Karma: 34

Grokking: When AI Sud­denly Starts to Understand

Strad Slater1 Dec 2025 8:00 UTC
4 points
1 comment4 min readEA link
(williamslater2003.medium.com)

How Good­fire Is Turn­ing AI In­ter­pretabil­ity Into Real Products

Strad Slater30 Nov 2025 11:00 UTC
0 points
0 comments4 min readEA link
(williamslater2003.medium.com)

4 Les­sons From An­thropic on Scal­ing In­ter­pretabil­ity Research

Strad Slater29 Nov 2025 11:22 UTC
4 points
0 comments4 min readEA link
(williamslater2003.medium.com)

Why Ex­plain­ing AI Is Not the Same as Un­der­stand­ing It

Strad Slater28 Nov 2025 10:38 UTC
2 points
0 comments4 min readEA link
(williamslater2003.medium.com)

Reflec­tions on Dario Amodei’s ‘Ur­gency of In­ter­pretabil­ity’

Strad Slater27 Nov 2025 8:30 UTC
2 points
0 comments5 min readEA link
(williamslater2003.medium.com)

The Causal In­ner Product: How LLMs Turn Con­cepts Into Direc­tions (Part 2)

Strad Slater26 Nov 2025 11:03 UTC
2 points
0 comments4 min readEA link
(williamslater2003.medium.com)

In­side the Lin­ear Rep­re­sen­ta­tion Hy­poth­e­sis: How LLMs Turn Con­cepts Into Direc­tions (Part 1)

Strad Slater25 Nov 2025 11:26 UTC
4 points
0 comments4 min readEA link
(williamslater2003.medium.com)

The Hid­den Prob­lem In­side Every AI Model: Superposition

Strad Slater24 Nov 2025 10:14 UTC
4 points
1 comment4 min readEA link
(williamslater2003.medium.com)

Good­fire — The Startup Try­ing to De­code How AI Thinks

Strad Slater23 Nov 2025 10:22 UTC
2 points
1 comment5 min readEA link
(williamslater2003.medium.com)

Are AI Models Es­cap­ing Plato’s Cave?

Strad Slater22 Nov 2025 11:46 UTC
2 points
0 comments5 min readEA link
(williamslater2003.medium.com)

The Univer­sal­ity Hy­poth­e­sis — Do All AI Models Think The Same?

Strad Slater21 Nov 2025 10:55 UTC
2 points
0 comments4 min readEA link
(williamslater2003.medium.com)

Mechanis­tic In­ter­pretabil­ity — Make AI Safe By Un­der­stand­ing Them

Strad Slater20 Nov 2025 10:52 UTC
2 points
0 comments6 min readEA link
(williamslater2003.medium.com)

6 In­sights From An­thropic’s Re­cent Dis­cus­sion On LLM Interpretability

Strad Slater19 Nov 2025 10:51 UTC
2 points
0 comments5 min readEA link
(williamslater2003.medium.com)

6 Ways AI Can Harm You — and How to Stop It

Strad Slater18 Nov 2025 10:36 UTC
3 points
0 comments6 min readEA link
(williamslater2003.medium.com)

Why You Should Think About What You Tell ChatGPT : Data Pri­vacy In A World With AI

Strad Slater17 Nov 2025 10:15 UTC
2 points
1 comment5 min readEA link
(williamslater2003.medium.com)

How I Deal With My Anx­iety Around AI

Strad Slater16 Nov 2025 11:30 UTC
4 points
0 comments4 min readEA link
(williamslater2003.medium.com)

Do Hu­mans Have A Com­pet­i­tive Edge Against AGI?

Strad Slater15 Nov 2025 10:20 UTC
4 points
0 comments7 min readEA link
(williamslater2003.medium.com)

Why ChatGPT Can’t Be Your Therapist

Strad Slater14 Nov 2025 10:07 UTC
13 points
0 comments4 min readEA link
(williamslater2003.medium.com)

The Need for an Effec­tive AI In­ci­dent Re­port­ing Framework

Strad Slater13 Nov 2025 8:53 UTC
2 points
0 comments4 min readEA link
(williamslater2003.medium.com)

The Merge: A Po­ten­tially Pos­i­tive Fu­ture with Su­per Intelligence

Strad Slater12 Nov 2025 8:00 UTC
2 points
0 comments4 min readEA link
(williamslater2003.medium.com)