News

lesswrong. com
lesswrong. com > posts > u Lk7xi Qb Antb5h6 PB > iliad-is-hiring

Iliad is Hiring " Less Wrong

1+ hour, 18+ min ago  (456+ words) Iliad is hiring for operations, research, and engineering roles. If you're excited about advancing foundational AI alignment research, we'd love to hear from you. Full job descriptions are available at https: //www. iliad. ac/careers. About Iliad Iliad is a…...

Symbols: nasdaq:nbis,nyse:aon
lesswrong. com
lesswrong. com > posts > e PYru Mk Pjvn So BGAS > the-hats-of-lessonline

The Hats of Less Online " Less Wrong

5+ hour, 24+ min ago  (235+ words) It is currently the evening after day two of Less Online 2026. I wish to document one popular topic of discussion among Less Online attendees: golden h...

lesswrong. com
lesswrong. com > posts > Tm2d CH6d HE2ber53 Y > coalitional-darwinism-and-the-instrumental-utility-of

Coalitional Darwinism and the Instrumental Utility of Individuality " Less Wrong

1+ day, 1+ hour ago  (1339+ words) This post was written as part of MATS 9. 1 under the mentorship of Richard Ngo. "...

lesswrong. com
lesswrong. com > posts > bzk Qg Yha Ccpv Kqm AK > optimisation-over-non-stationary-distributions-creates

Optimisation over non-stationary distributions creates weirder minds " Less Wrong

1+ day, 14+ hour ago  (433+ words) Modern LLM post-training involves interleaving many different training objectives such as mixing different reward functions with supervised fine tuning (SFT), typically in order to guard against catastrophic forgetting. However, a lot of existing theoretical work in AI safety operates under…...

Symbols: opai.pvt,nasdaq:guru
lesswrong. com
lesswrong. com > posts > z LERn ZYLTPGqyfpqy > two-more-methods-for-consistency-training-and-some-new-ways-1

Two More Methods for Consistency Training and Some New Ways to Apply It " Less Wrong

1+ day, 17+ hour ago  (213+ words) Authors: Sukrati Gautam*, Neil Shah*, Arav Dhoot*, Bryan Maruyama*, Caroline Wei*, Rohan Kapoor, Robert Sidey, Prakhar Gupta, Zi Cheng Huang, David D...

lesswrong. com
lesswrong. com > posts > 5cn CF2 G6 CAYei Yo T5 > thoughts-on-learning-mechanics

Thoughts on 'Learning Mechanics' " Less Wrong

3+ day, 22+ hour ago  (388+ words) Last month, I stumbled upon an optimistic-sounding paper: "There Will Be a Scientific Theory of Deep Learning". "...

Symbols: scale-up
lesswrong. com
lesswrong. com > posts > LCrk93 DNWSudjp5rd > society-explained-a-tool-for-efficiently-exploring-greater

Society Explained: a tool for efficiently exploring >100 theories of society " Less Wrong

4+ day, 13+ min ago  (260+ words) There are many competing theories of how society does and should function, from Karl Marx and Adam Smith to Steven Pinker and Eliezer Yudkowsky. These theories are often hard to understand - you may need to read an entire book (or…...

lesswrong. com
lesswrong. com > posts > 3wq Zw XMz EAkd3m LLM > taking-the-training-wheels-off-aligning-llms-without

Taking the Training Wheels Off: Aligning LLMs without Personas " Less Wrong

5+ day, 7+ hour ago  (281+ words) " If you told an AI Alignment researcher in 2018 about an alignment plan that involved collecting trajectory information of moral experts at scale...

lesswrong. com
lesswrong. com > posts > PDh Zx Rsizu Gj Bu6ze > can-llms-even-teach-exploring-the-teacher-axis

Can LLMs even teach? Exploring the Teacher Axis " Less Wrong

5+ day, 17+ hour ago  (1375+ words) TLDR As a passionate teacher, it has pained my heart to watch my students lose deeper critical thinking skills and independent reasoning. But attempt...

Symbols: btc-usd,eth-usd,xrp-usd,btc-eur,sol-usd
lesswrong. com
lesswrong. com > posts > tm Wx DGnu Nda HFDyjf > dissolving-the-deep-learning-sample-efficiency-gap-1

Dissolving the Deep Learning Sample Efficiency Gap " Less Wrong

5+ day, 19+ hour ago  (612+ words) A common observation about deep learning is that it's wildly sample inefficient compared to humans. Deep learning systems appear to need much more re...

Symbols: btc-usd