irthomasthomas's favorites

1.		Using Claude Code: The unreasonable effectiveness of HTML (twitter.com/trq212)
		517 points by pretext 2 days ago \| 270 comments
2.		Principles for agent-native CLIs (twitter.com/trevin)
		110 points by blumpy22 3 days ago \| 50 comments
3.		ProgramBench: Can language models rebuild programs from scratch? (arxiv.org)
		150 points by jonbaer 4 days ago \| 79 comments
4.		The text mode lie: why modern TUIs are a nightmare for accessibility (xogium.me)
		295 points by SpyCoder77 7 days ago \| 137 comments
5.		Microsoft and OpenAI end their exclusive and revenue-sharing deal (bloomberg.com)
		990 points by helsinkiandrew 14 days ago \| 845 comments
6.		Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview (github.com/dirac-run)
		393 points by GodelNumbering 14 days ago \| 148 comments
7.		Scoring Show HN submissions for AI design patterns (adriankrebs.ch)
		333 points by hubraumhugo 18 days ago \| 235 comments
8.		Laws of Software Engineering (lawsofsoftwareengineering.com)
		1172 points by milanm081 20 days ago \| 530 comments
9.		AI assistance when contributing to the Linux kernel (github.com/torvalds)
		527 points by hmokiguess 30 days ago \| 436 comments
10.		Research-Driven Agents: When an agent reads before it codes (skypilot.co)
		214 points by hopechong 31 days ago \| 54 comments
11.		Little Snitch comes to Linux, but the core logic is closed source (unknown-universe.co.uk)
		80 points by TheIPW 31 days ago \| 26 comments
12.		Git commands I run before reading any code (piechowski.io)
		2338 points by grepsedawk 33 days ago \| 509 comments
13.		Claude mixes up who said what (dwyer.co.za)
		467 points by sixhobbits 32 days ago \| 360 comments
14.		Writing Lisp is AI resistant and I'm sad (djhaskin.com)
		99 points by djha-skin 36 days ago \| 100 comments
15.		Shell Tricks That Make Life Easier (and Save Your Sanity) (hofstede.it)
		649 points by zdw 46 days ago \| 280 comments
16.		Ask HN: AI productivity gains – do you fire devs or build better products?
		114 points by Bleiglanz 50 days ago \| 204 comments
17.		Common Lisp Development Tooling (creativetension.co)
		120 points by 0bytematt 50 days ago \| 29 comments
18.		Autoresearch Hub (autoresearchhub.com)
		73 points by EvgeniyZh 58 days ago \| 32 comments
19.		Grandparents are glued to their phones [video] (bbc.com)
		206 points by tartoran 56 days ago \| 148 comments
20.		Getting Started in Common Lisp (lisp-stat.dev)
		88 points by oumua_don17 62 days ago \| 36 comments
21.		Files are the interface humans and agents interact with (madalitso.me)
		296 points by malgamves 65 days ago \| 132 comments
22.		You need to rewrite your CLI for AI agents (poehnelt.com)
		163 points by justinwp 67 days ago \| 67 comments
23.		If AI writes code, should the session be part of the commit? (github.com/mandel-macaque)
		497 points by mandel_x 70 days ago \| 391 comments
24.		Right-sizes LLM models to your system's RAM, CPU, and GPU (github.com/alexsjones)
		301 points by bilsbie 70 days ago \| 70 comments
25.		What does " 2>&1 " mean? (stackoverflow.com)
		429 points by alexmolas 73 days ago \| 250 comments
26.		Show HN: Beehive – Multi-Workspace Agent Orchestrator (storozhenko98.github.io)
		47 points by mst98 76 days ago \| 22 comments
27.		Show HN: Agent Swarm – Multi-agent self-learning teams (OSS) (github.com/desplega-ai)
		63 points by tarasyarema 74 days ago \| 46 comments
28.		Just-bash: Bash for Agents (github.com/vercel-labs)
		124 points by tosh 74 days ago \| 69 comments
29.		Aqua: A CLI message tool for AI agents (github.com/quailyquaily)
		76 points by lyricat 77 days ago \| 33 comments
30.		I found a useful Git one liner buried in leaked CIA developer docs (spencer.wtf)
		708 points by spencerldixon 79 days ago \| 255 comments
		More