stephankoelle's favorites

1.		Self-updating screenshots (interblah.net)
		452 points by bjhess 1 day ago \| 70 comments
2.		TurboQuant: A first-principles walkthrough (arkaung.github.io)
		278 points by kweezar 18 hours ago \| 56 comments
3.		SWE-bench Verified no longer measures frontier coding capabilities (openai.com)
		339 points by kmdupree 1 day ago \| 178 comments
4.		Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git) (github.com/nex-crm)
		257 points by najmuzzaman 2 days ago \| 113 comments
5.		Sabotaging projects by overthinking, scope creep, and structural diffing (kevinlynagh.com)
		527 points by alcazar 3 days ago \| 141 comments
6.		Bitwarden CLI compromised in ongoing Checkmarx supply chain campaign (socket.dev)
		867 points by tosh 4 days ago \| 425 comments
7.		Website streamed live directly from a model (flipbook.page)
		435 points by sethbannon 5 days ago \| 118 comments
8.		5x5 Pixel font for tiny screens (maurycyz.com)
		818 points by zdw 8 days ago \| 158 comments
9.		Laws of Software Engineering (lawsofsoftwareengineering.com)
		1165 points by milanm081 6 days ago \| 524 comments
10.		Migrating from DigitalOcean to Hetzner (isayeter.com)
		893 points by yusufusta 9 days ago \| 430 comments
11.		Are the costs of AI agents also rising exponentially? (2025) (tobyord.com)
		306 points by louiereederson 12 days ago \| 134 comments
12.		Android CLI: Build Android apps 3x faster using any agent (googleblog.com)
		314 points by ingve 11 days ago \| 138 comments
13.		Do you even need a database? (dbpro.app)
		309 points by upmostly 12 days ago \| 297 comments
14.		Introspective Diffusion Language Models (introspective-diffusion.github.io)
		281 points by zagwdt 13 days ago \| 55 comments
15.		Small models also found the vulnerabilities that Mythos found (aisle.com)
		1284 points by dominicq 16 days ago \| 341 comments
16.		I just want simple S3 (feld.me)
		247 points by g0xA52A2A 16 days ago \| 127 comments
17.		Kagi Product Tips – Customize Your Search Results with URL Redirects (kagi.com)
		186 points by treetalker 17 days ago \| 37 comments
18.		The Raft consensus algorithm explained through "Mean Girls" (2019) (cockroachlabs.com)
		136 points by vermilingua 17 days ago \| 29 comments
19.		Understanding Traceroute (stonecharioteer.com)
		177 points by stonecharioteer 21 days ago \| 25 comments
20.		Show HN: Is Hormuz open yet? (ishormuzopenyet.com)
		484 points by anonfunction 18 days ago \| 209 comments
21.		MegaTrain: Full Precision Training of 100B+ Parameter LLMs on a Single GPU (arxiv.org)
		326 points by chrsw 19 days ago \| 57 comments
22.		Dropping Cloudflare for Bunny.net (jola.dev)
		415 points by shintoist 20 days ago \| 211 comments
23.		Show HN: I built a tiny LLM to demystify how language models work (github.com/arman-bd)
		915 points by armanified 21 days ago \| 134 comments
24.		Show HN: Gemma Gem – AI model embedded in a browser – no API keys, no cloud (github.com/kessler)
		156 points by ikessler 21 days ago \| 21 comments
25.		LLM Wiki – example of an "idea file" (gist.github.com)
		296 points by tamnd 23 days ago \| 95 comments
26.		OpenScreen is an open-source alternative to Screen Studio (github.com/siddharthvaddem)
		434 points by jskopek 26 days ago \| 73 comments
27.		How many products does Microsoft have named 'Copilot'? (teybannerman.com)
		815 points by gpi 23 days ago \| 386 comments
28.		The CMS is dead, long live the CMS (jazzsequence.com)
		159 points by taubek 23 days ago \| 98 comments
29.		Emotion concepts and their function in a large language model (anthropic.com)
		191 points by dnw 23 days ago \| 204 comments
30.		We replaced RAG with a virtual filesystem for our AI documentation assistant (mintlify.com)
		411 points by denssumesh 25 days ago \| 151 comments
		More

HN For You