curius graph
☾
Dark
all pages
search
showing 3451-3500 of 198841 pages (sorted by popularity)
« prev
1
...
68
69
70
71
72
...
3977
next »
Emmi Wu Portfolio
5 users ▼
Strangely, Matrix Multiplications on GPUs Run Faster When Given "Predictable" Data! [short]
5 users ▼
I've been thinking about conviction | Andy Kong
5 users ▼
Some thoughts on writing
5 users ▼
my life outside
5 users ▼
Why the French Don’t Obsess Over Purpose - by Pamela Clapp
5 users ▼
Against truth - by Sam Kriss - Numb at the Lodge
5 users ▼
Rostra
5 users ▼
Gamma App
5 users ▼
50 things I know - by Sasha Chapin - Sasha's 'Newsletter'
5 users ▼
Quarter Mile
5 users ▼
Prolegomena to a Theory of Fun - LessWrong
5 users ▼
How to Make Wealth
5 users ▼
i don't believe in marriage - by Lilian Caylee
5 users ▼
Anatomy of a Modern Finetuning API
5 users ▼
Making Software: Shaders.
5 users ▼
Why I'm unreachable and maybe you should be too
5 users ▼
Rewind
5 users ▼
Founder Mode
5 users ▼
Stripe’s payments APIs: the first ten years
5 users ▼
The Structure of Stand-Up Comedy
5 users ▼
BetterExplained – Math lessons that click
5 users ▼
Alignment likely generalizes further than capabilities.
5 users ▼
Infinitely many stages of grief – Power Overwhelming
5 users ▼
Non-determinism in GPT-4 is caused by Sparse MoE - 152334H
5 users ▼
Steering GPT-2-XL by adding an activation vector — LessWrong
5 users ▼
Singular value decomposition - Wikipedia
5 users ▼
SAE feature geometry is outside the superposition hypothesis — LessWrong
5 users ▼
Advice invitation - Alexey Guzey
5 users ▼
Circuits Updates - July 2024
5 users ▼
actual conversations i definitely had at sparc | Infinite Ascent
5 users ▼
The Opposite of Shame | The On Being Project
5 users ▼
Give yourself a speed limit | Infinite Ascent
5 users ▼
Why I'm becoming disillusioned with Effective Altruism
5 users ▼
Post 33: Seek Upside Risk — Neel Nanda
5 users ▼
Pointer Pointer
5 users ▼
The Gentle Romance - by Richard Ngo - Asimov Press
5 users ▼
[2502.17424] Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
5 users ▼
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
5 users ▼
INVESTIGATION: Uncovering Chinese Academic Espionage at Stanford
5 users ▼
leogao's Shortform — LessWrong
5 users ▼
On love & relationships | Evan Conrad
5 users ▼
Do reasoning models use their scratchpad like we do? Evidence from distilling paraphrases
5 users ▼
bo on X: "performative curius highlighting" / X
5 users ▼
Towards a Typology of Strange LLM Chains-of-Thought
5 users ▼
Are you a jerk, or a liar? - by Cate Hall - Useful Fictions
5 users ▼
Chautauqua: an idea embedded in a place | devonzuegel.com
5 users ▼
The Alien Style of Deep Learning Generative Design | by Carlos E. Perez
5 users ▼
mangotango
5 users ▼
It’s Time to Build | Andreessen Horowitz
5 users ▼
« prev
1
...
68
69
70
71
72
...
3977
next »