krackers's favorites | Hacker News

1.		Mechanisms of introspective awareness in LLMs [pdf] (arxiv.org)
		2 points by ryeights 4 days ago \| 2 comments
2.		A simplified model of Fil-C (corsix.org)
		207 points by aw1621107 3 days ago \| 131 comments
3.		The M×N problem of tool calling and open-source models (thetypicalset.com)
		158 points by remilouf 11 days ago \| 49 comments
4.		Phyphox – Physical Experiments Using a Smartphone (phyphox.org)
		256 points by _Microft 8 days ago \| 42 comments
5.		Most people can't juggle one ball (lesswrong.com)
		507 points by surprisetalk 11 days ago \| 174 comments
6.		I still prefer MCP over skills (david.coffee)
		460 points by gmays 11 days ago \| 375 comments
7.		[flagged] More likely than not you're using bubble wrap wrong (bookofjoe2.blogspot.com)
		17 points by surprisetalk 13 days ago \| 18 comments
8.		Six (and a half) intuitions for KL divergence (perfectlynormal.co.uk)
		114 points by jxmorris12 13 days ago \| 33 comments
9.		Porting Go's strings package to C (antonz.org)
		73 points by ingve 17 days ago \| 14 comments
10.		Apple Rich Text Fundamentals (paper.pro)
		10 points by tobr 18 days ago
11.		We replaced RAG with a virtual filesystem for our AI documentation assistant (mintlify.com)
		411 points by denssumesh 18 days ago \| 151 comments
12.		Async Python Is Secretly Deterministic (dbos.dev)
		79 points by KraftyOne 17 days ago \| 36 comments
13.		Modern SQLite: Features You Didn't Know It Had (slicker.me)
		244 points by thunderbong 18 days ago \| 63 comments
14.		Show HN: Git bayesect – Bayesian Git bisection for non-deterministic bugs (github.com/hauntsaninja)
		337 points by hauntsaninja 23 days ago \| 43 comments
15.		Intuiting Pratt Parsing (louis.co.nz)
		169 points by signa11 21 days ago \| 48 comments
16.		Good CTE, Bad CTE (boringsql.com)
		203 points by radimm 22 days ago \| 45 comments
17.		TurboQuant: Redefining AI efficiency with extreme compression (research.google)
		576 points by ray__ 27 days ago \| 166 comments
18.		LLM Neuroanatomy II: Modern LLM Hacking and Hints of a Universal Language? (dnhkng.github.io)
		147 points by realberkeaslan 27 days ago \| 41 comments
19.		Finding all regex matches has always been O(n²) (iev.ee)
		260 points by lalitmaganti 32 days ago \| 70 comments
20.		An unsolicited guide to being a researcher [pdf] (emerge-lab.github.io)
		217 points by sebg 32 days ago \| 24 comments
21.		The LCA problem revisited [pdf] (stonybrook.edu)
		37 points by remywang 34 days ago \| 7 comments
22.		The Shape of Inequalities (andreinc.net)
		122 points by nomemory 32 days ago \| 24 comments
23.		JPEG Compression (sophielwang.com)
		399 points by vinhnx 38 days ago \| 125 comments
24.		Using calculus to do number theory (hidden-phenomena.com)
		136 points by cpp_frog 35 days ago \| 21 comments
25.		Claude Agent Skills: A First Principles Deep Dive (2025) (leehanchung.github.io)
		3 points by dnw 81 days ago
26.		Python: The Optimization Ladder (cemrehancavdar.com)
		349 points by Twirrim 41 days ago \| 146 comments
27.		Okmain: How to pick an OK main colour of an image (dgroshev.com)
		253 points by dgroshev 42 days ago \| 47 comments
28.		Executing programs inside transformers with exponentially faster inference (percepta.ai)
		330 points by u1hcw9nx 39 days ago \| 130 comments
29.		Faster asin() was hiding in plain sight (16bpp.net)
		263 points by def-pri-pub 40 days ago \| 130 comments
30.		Tinnitus Is Connected to Sleep (sciencealert.com)
		236 points by bookofjoe 44 days ago \| 253 comments
		More