Skip To Main Content
Steven Byrnes on Muck Rack

Steven Byrnes

Boston
As seen in: Substack, iVoox Podcast and Radio, Hi-Desert Star, CITR (Vancouver, BC), Town Times (Watertown, CT), Fatea Magazine, LessWrong (30+ Karma)
Researching Artificial General Intelligence Safety, via thinking about neuroscience and algorithms. @AsteraInstitute. For substack etc see sjbyrnes.com
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile

Get in touch with Steven

Contact Steven, search articles and posts on X, monitor coverage, and track replies from one place.

Learn more about Muck Rack

Actions

Share this page

Is this you?

As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile

Articles

LLMs are (still) mostly powered by imitative learning, not RL

|
By Steven Byrnes, Oliver Sourbut
| LessWrong (30+ Karma)
Reinforcement learning from verifiable rewards (RLVR) is the hot new thing in LLM training. It’s so hot, and people spend so much time talking about it, that they sometimes lose sight of the big picture. Stepping back, LLMs can do lots of very impressive things. How? Where did those capabilities come from? Fundamentally, they come from a combination of: (1) Imitative learning, including pretraining and supervised fine-tuning (SFT) See my earlier discussion: .
Open in Who Shared Issue with article?

Notes on technical alignment via human-like social drives

|
By Steven Byrnes
| LessWrong (30+ Karma)
1.1 Backstory for this post As discussed in Intro to Brain-Like-AGI Safety, I’m working on the technical alignment problem for a hypothetical future “brain-like AGI”, with a particular focus on treating human innate social and moral drives as a possible jumping-off point for our technical alignment approach.
Open in Who Shared Issue with article?

Sympathy for both sides of the egregious misalignment debate

|
By Steven Byrnes
| LessWrong (30+ Karma)
On one side of this debate is Yudkowsky & Soares, who think that (if AI progress continues) we’re on a direct path to egregiously-misaligned, scheming, out-of-control, rogue superintelligence (ASI), not even slightly nice, in the absence of yet-to-be-invented breakthrough technical alignment ideas.
Open in Who Shared Issue with article?
See all 345 articles