john-shaffer's favorites

1.		Show HN: Value likelihoods for OpenAI structured output (arena-ai.github.io)
		113 points by ngrislain 2 days ago \| 40 comments
2.		Cognitive load is what matters (minds.md)
		1769 points by zdw 25 days ago \| 721 comments
3.		JEP 483: Ahead-of-Time Class Loading and Linking (openjdk.org)
		148 points by ptx 26 days ago \| 38 comments
4.		OpenAI O3 breakthrough high score on ARC-AGI-PUB (arcprize.org)
		1724 points by maurycy 27 days ago \| 1755 comments
5.		Video Surveillance with YOLO+llava (github.com/psychip)
		261 points by psychip 3 months ago \| 68 comments
6.		Datomic and Content Addressable Techniques (latacora.com)
		166 points by lvh 4 months ago \| 40 comments
7.		Critical vulnerabilities in 6 AWS services disclosed at Black Hat USA (scmagazine.com)
		55 points by noctarius 5 months ago \| 19 comments
8.		A skeptic's first contact with Kubernetes (davidv.dev)
		167 points by todsacerdoti 5 months ago \| 101 comments
9.		Launch HN: Undermind (YC S24) – AI agent for discovering scientific papers
		292 points by jramette 5 months ago \| 126 comments
10.		Unfashionably secure: why we use isolated VMs (thinkst.com)
		305 points by mh_ 5 months ago \| 243 comments
11.		Software engineers are not (and should not be) technicians (haskellforall.com)
		65 points by dahlia 5 months ago \| 82 comments
12.		Story points are pointless, measure queues (brightball.com)
		345 points by brightball 6 months ago \| 288 comments
13.		My finetuned models beat OpenAI's GPT-4 (mlops.systems)
		414 points by majc2 6 months ago \| 91 comments
14.		Microsoft Chose Profit over Security, Whistleblower Says (propublica.org)
		676 points by tyleroconnell 7 months ago \| 305 comments
15.		Silicon Valley's best kept secret: Founder liquidity (stefantheard.com)
		1811 points by mooreds 7 months ago \| 914 comments
16.		Simple tasks showing reasoning breakdown in state-of-the-art LLMs (arxiv.org)
		375 points by tosh 7 months ago \| 380 comments
17.		After 6 years, I'm over GraphQL (bessey.dev)
		1259 points by mattbessey 7 months ago \| 698 comments
18.		Rete algorithm (wikipedia.org)
		216 points by skilled 7 months ago \| 54 comments
19.		My VM is lighter (and safer) than your container (2017) (acm.org)
		168 points by fanf2 8 months ago \| 174 comments
20.		Launch HN: Muddy (YC S19) – Multiplayer browser for getting work done
		252 points by lele0108 8 months ago \| 110 comments
21.		A useful front-end confetti animation library (github.com/catdad)
		482 points by blini2077 8 months ago \| 118 comments
22.		Distributed Authorization (osohq.com)
		150 points by AnhTho_FR 9 months ago \| 64 comments
23.		First impressions of early-access GPT-4 fine-tuning (supersimple.io)
		27 points by gmays 9 months ago \| 3 comments
24.		Building reliable systems out of unreliable agents (rainforestqa.com)
		295 points by fredsters_s 9 months ago \| 54 comments
25.		More Agents Is All You Need: LLMs performance scales with the number of agents (arxiv.org)
		288 points by TaurenHunter 9 months ago \| 206 comments
26.		RAGFlow is an open-source RAG engine based on OCR and document parsing (github.com/infiniflow)
		230 points by marban 9 months ago \| 53 comments
27.		Linux Crisis Tools (brendangregg.com)
		596 points by samber 9 months ago \| 124 comments
28.		Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking (arxiv.org)
		280 points by hackerlight 10 months ago \| 264 comments
29.		Show HN: LlamaGym – fine-tune LLM agents with online reinforcement learning (github.com/khoomeik)
		239 points by KhoomeiK 10 months ago \| 28 comments
30.		Self-Retrieval: Building an information retrieval system with one LLM (arxiv.org)
		200 points by PaulHoule 10 months ago \| 29 comments
		More