raducu's favorites | Hacker News

1.		The local LLM ecosystem doesn’t need Ollama (sleepingrobots.com)
		634 points by Zetaphor 2 days ago \| 208 comments
2.		Distributed DuckDB Instance (github.com/citguru)
		185 points by citguru 4 days ago \| 36 comments
3.		Design and implementation of DuckDB internals (duckdb.org)
		201 points by mpweiher 7 days ago \| 17 comments
4.		Building a SaaS in 2026 Using Only EU Infrastructure (eualternative.eu)
		194 points by sparkling 5 days ago \| 61 comments
5.		I still prefer MCP over skills (david.coffee)
		460 points by gmays 8 days ago \| 375 comments
6.		Gemma 4 on iPhone (apps.apple.com)
		868 points by janandonly 12 days ago \| 234 comments
7.		So where are all the AI apps? (answer.ai)
		452 points by tanelpoder 24 days ago \| 422 comments
8.		“Collaboration” is bullshit (joanwestenberg.com)
		363 points by mitchbob 26 days ago \| 187 comments
9.		Apideck CLI – An AI-agent interface with much lower context consumption than MCP (apideck.com)
		137 points by gertjandewilde 32 days ago \| 123 comments
10.		The 100 hour gap between a vibecoded prototype and a working product (macbudkowski.com)
		262 points by kiwieater 33 days ago \| 331 comments
11.		A Visual Introduction to Machine Learning (2015) (r2d3.us)
		399 points by vismit2000 34 days ago \| 30 comments
12.		US private credit defaults hit record 9.2% in 2025, Fitch says (marketscreener.com)
		436 points by JumpCrisscross 36 days ago \| 464 comments
13.		LLMs work best when the user defines their acceptance criteria first (katanaquant.com)
		461 points by dnw 42 days ago \| 423 comments
14.		Tinnitus Is Connected to Sleep (sciencealert.com)
		236 points by bookofjoe 41 days ago \| 253 comments
15.		Qwen3.5 Fine-Tuning Guide (unsloth.ai)
		416 points by bilsbie 44 days ago \| 107 comments
16.		GPT-5.4 (openai.com)
		1019 points by mudkipdev 43 days ago \| 807 comments
17.		Nvidia PersonaPlex 7B on Apple Silicon: Full-Duplex Speech-to-Speech in Swift (ivan.digital)
		374 points by ipotapov 44 days ago \| 125 comments
18.		Google Workspace CLI (github.com/googleworkspace)
		953 points by gonzalovargas 44 days ago \| 285 comments
19.		Large-Scale Online Deanonymization with LLMs (simonlermen.substack.com)
		364 points by DalasNoin 52 days ago \| 234 comments
20.		Learnings from 4 months of Image-Video VAE experiments (linum.ai)
		129 points by schopra909 52 days ago \| 16 comments
21.		IDF killed Gaza aid workers at point blank range in 2025 massacre: Report (dropsitenews.com)
		2084 points by Qem 52 days ago \| 997 comments
22.		FreeBSD doesn't have Wi-Fi driver for my old MacBook, so AI built one for me (vladimir.varank.in)
		434 points by varankinv 53 days ago \| 361 comments
23.		AI adoption and Solow's productivity paradox (fortune.com)
		792 points by virgildotcodes 59 days ago \| 752 comments
24.		Evaluating AGENTS.md: are they helpful for coding agents? (arxiv.org)
		232 points by mustaphah 60 days ago \| 161 comments
25.		SkillsBench: Benchmarking how well agent skills work across diverse tasks (arxiv.org)
		364 points by mustaphah 60 days ago \| 171 comments
26.		Breaking the spell of vibe coding (fast.ai)
		434 points by arjunbanker 63 days ago \| 348 comments
27.		“Nothing” is the secret to structuring your work (vangemert.dev)
		444 points by spmvg 68 days ago \| 184 comments
28.		Eight more months of agents (crawshaw.io)
		223 points by arrowsmith 69 days ago \| 241 comments
29.		Claude Code is being dumbed down? (symmetrybreak.ing)
		1085 points by WXLCKNO 65 days ago \| 701 comments
30.		GPT‑5.3‑Codex‑Spark (openai.com)
		890 points by meetpateltech 64 days ago \| 387 comments
		More