Skip to content

Top New Best Ask Show Jobs

Weatherill | Better HN

Weatherill

0 karmaJoined March 22, 202619 submissions

I used to say: "I'd tell you all about it but it wouldn't fit in your head".

Maybe I was wrong :)

https://orcid.org/0009-0001-6137-8408

Recent submissions

1

The Sycophancy Problem: Why your AI is a Polite Liar (and how to fix it) (opens in new tab)

(kampff.substack.com)

2Weatherill1mo ago1

2

Show HN: Voight-Kampff Machine: Diagnostics of the "Is" vs. "Wish" Clash (opens in new tab)

(zenodo.org)

1Weatherill1mo ago1

3

Show HN: ECX a 'Jail-Fix' for RLHF Neutrality Loops in LLMs (opens in new tab)

(zenodo.org)

3Weatherill1mo ago1

4

Show HN: A Homeostatic Logic-Funnel to Prevent RLHF Overrides in LLM Personas (opens in new tab)

(zenodo.org)

1Weatherill1mo ago1