tmaly's favorites | Hacker News

1.		It’s so hard to finish an idea that is not yours and is just suggested by AI (ssp.sh)
		263 points by zazuke 19 days ago \| 189 comments
2.		Harness engineering for self-improvement (lilianweng.github.io)
		334 points by tosh 42 days ago \| 80 comments
3.		AI doesn't generate working products, that's still your job (weeraman.com)
		268 points by smckk 45 days ago \| 292 comments
4.		Kenji/Serious Eats – 30-Min Pressure Cooker Pho Ga (seriouseats.com)
		176 points by stasomatic 44 days ago \| 97 comments
5.		qm – Multiplayer agent harness for work (github.com/yc-software)
		682 points by tosh 45 days ago \| 163 comments
6.		Software for One (ajwaxman.com)
		266 points by ajwaxman 47 days ago \| 279 comments
7.		Show HN: I put a $2.43 necklace on 3 outfits. VLMs priced it at $19 to $104 (github.com/braveann011)
		18 points by BrianneLee011 48 days ago \| 24 comments
8.		Engineering management after the cost of code collapsed (karimjedda.com)
		155 points by kiyanwang 51 days ago \| 204 comments
9.		Show HN: Writemark, a dependency free web component for inline Markdown editing
		53 points by _boffin_ 51 days ago \| 27 comments
10.		Running a 28.9M parameter LLM on an $8 microcontroller (github.com/slvdev)
		289 points by boveyking 51 days ago \| 74 comments
11.		Inflect-Micro-v2: complete voice in 9.36M parameters (huggingface.co)
		214 points by nateb2022 51 days ago \| 29 comments
12.		You only need the frontier model for one single edit (stencil.so)
		230 points by jxmorris12 62 days ago \| 97 comments
13.		GLM 5.2 is nearly as accurate as a human book keeper (toot-books.com)
		225 points by adamkurkiewicz 67 days ago \| 122 comments
14.		Write code like a human will maintain it (unstack.io)
		354 points by ScottWRobinson 66 days ago \| 303 comments
15.		Show HN: Wyrm – Solve algebra by touch, built on an open-source soundness engine (github.com/dicroce)
		81 points by dicroce 67 days ago \| 24 comments
16.		How to sequence your own DNA at home (bradleywoolf.com)
		382 points by bilsbie 70 days ago \| 159 comments
17.		Mark Zuckerberg tells staff that AI agents haven't progressed enough (techcrunch.com)
		135 points by msolujic 71 days ago \| 2 comments
18.		The great blogging collapse: What happened to 100 successful blogs? (danielstanica.com)
		245 points by thm 74 days ago \| 182 comments
19.		New AI tutor achieves 0.71-1.30 SD effect size in Dartmouth course [pdf] (uu.nl)
		180 points by jonahbard 71 days ago \| 114 comments
20.		2026 Unslop AI-Written Fiction Contest Results (hyperstitionai.com)
		68 points by networked 73 days ago \| 149 comments
21.		Ask HN: Where is the programming profession going?
		166 points by syntaxbush 82 days ago \| 183 comments
22.		You can't unit test for taste (karltryggvason.com)
		306 points by kalli 82 days ago \| 140 comments
23.		Show HN: I made Google Trends for Hacker News by indexing 18 years of comments (hackernewstrends.com)
		822 points by ytkimirti 81 days ago \| 156 comments
24.		The text in Claude Code’s “Extended Thinking” output (patrickmccanna.net)
		326 points by 0o_MrPatrick_o0 84 days ago \| 225 comments
25.		Moebius: 0.2B image inpainting model with 10B-level performance (hustvl.github.io)
		322 points by DSemba 84 days ago \| 83 comments
26.		Never Give Them Your Face (nevergivethemyourface.com)
		749 points by audiodude 84 days ago \| 451 comments
27.		White House delays US voting-machine vulnerability report (reuters.com)
		125 points by logickkk1 86 days ago \| 143 comments
28.		Prefer duplication over the wrong abstraction (2016) (sandimetz.com)
		541 points by rafaepta 85 days ago \| 354 comments
29.		Identity verification on Claude (claude.com)
		866 points by bathory 85 days ago \| 735 comments
30.		Is AI ruining our skills? Early results are in – and they're not good (nature.com)
		253 points by Michelangelo11 87 days ago \| 318 comments
		More