more dv_dt's favorites

31.		Unit Tests for LLMs?
		6 points by simantakDabhade 31 days ago \| 4 comments
32.		Ask HN: How do you analyze conversations with AI agents in your products?
		3 points by BohdanPetryshyn 34 days ago \| 2 comments
33.		The Obsessively Complete Infocom Catalog (eblong.com)
		126 points by exvi 33 days ago \| 53 comments
34.		Qwen3-VL (qwen.ai)
		434 points by natrys 37 days ago \| 160 comments
35.		Apple Photos app corrupts images (tenderlovemaking.com)
		1214 points by pattyj 43 days ago \| 439 comments
36.		RustGPT: A pure-Rust transformer LLM built from scratch (github.com/tekaratzas)
		369 points by amazonhut 45 days ago \| 174 comments
37.		Jef Raskin's cul-de-sac and the quest for the humane computer (arstechnica.com)
		59 points by pinewurst 48 days ago \| 18 comments
38.		How WASM DB and worker messaging helped me handle 500MB in 2s in browser
		6 points by vinserello 45 days ago \| 2 comments
39.		Ask HN: Costs for US sales tax compliance for a two-sided marketplace
		4 points by throway-9998888 45 days ago \| 3 comments
40.		What makes Claude Code so damn good (minusx.ai)
		469 points by samuelstros 68 days ago \| 304 comments
41.		Ask HN: How do you handle VAT / Sales Tax accounting as B2C SaaS?
		97 points by throw_1VJ51pMb 7 months ago \| 86 comments
42.		Qwen3-Next (qwen.ai)
		569 points by tosh 48 days ago \| 230 comments
43.		Google Doesn't Rank My Site for My Own Brand Name
		45 points by hypeaccount 50 days ago \| 25 comments
44.		Hetzner Storage Boxes (hetzner.com)
		19 points by kblissett 49 days ago \| 10 comments
45.		Keeping secrets out of logs (2024) (reyes.sh)
		251 points by xk3 53 days ago \| 54 comments
46.		Evals are a scam. And we're being gaslit into believing they aren't (hacktrace.substack.com)
		3 points by Areibman 54 days ago
47.		GLM 4.5 with Claude Code (z.ai)
		213 points by vincirufus 54 days ago \| 84 comments
48.		Ask HN: Who is hiring? (September 2025)
		267 points by whoishiring 59 days ago \| 450 comments
49.		Show HN: Multi-Agent-Coder Is #12 on Stanford's TBench. Beats Claude Code (github.com/danau5tin)
		5 points by Danau5tin 57 days ago \| 1 comment
50.		'World Models,' an old idea in AI, mount a comeback (quantamagazine.org)
		211 points by warrenm 58 days ago \| 80 comments
51.		Don't Build Multi-Agents (cognition.ai)
		123 points by JnBrymn 58 days ago \| 89 comments
52.		A 'third way' between buying or renting? Swiss co-ops say they've found it (nytimes.com)
		54 points by lifeisstillgood 60 days ago \| 53 comments
53.		Trying to get error backtraces in Rust libraries right (iroh.computer)
		78 points by emschwartz 64 days ago \| 62 comments
54.		The Theoretical Limitations of Embedding-Based Retrieval (arxiv.org)
		151 points by fzliu 62 days ago \| 38 comments
55.		Essential Coding Theory [pdf] (buffalo.edu)
		377 points by ibobev 62 days ago \| 63 comments
56.		Ask HN: Anyone working on bringing software back from US clouds?
		10 points by sam_lowry_ 63 days ago \| 11 comments
57.		Unexpected productivity boost of Rust (lubeno.dev)
		525 points by bkolobara 64 days ago \| 505 comments
58.		Memento: Fine-tuning LLM Agents without Fine-tuning LLMs (arxiv.org)
		1 point by vincirufus 65 days ago \| 1 comment
59.		Project Two – Creating Mobile App Using Tauri and Svelte (minosiants.com)
		3 points by thunderbong 65 days ago
60.		In-Memory Filesystems in Rust (arko.net)
		125 points by ingve 67 days ago \| 55 comments
		More