Costco Is the Anti-Amazon
Article URL: https://phenomenalworld.org/analysis/the-anti-amazon/ Comments URL: https://news.ycombinator.com/item?id=48776044 Points: 17 # Comments: 4
Latest
Factories Are Just Rooms
Article URL: https://interconnected.org/home/2026/07/03/factories Comments URL: https://news.ycombinator.com/item?id=48776035 Points: 4 # Comments: 0
America, 1926: What a Forgotten 100-Year-Old Report Says About Who We Are
Article URL: https://www.derekthompson.org/p/america-1926-an-absurdly-deep-dive Comments URL: https://news.ycombinator.com/item?id=48775979 Points: 4 # Comments: 0
Best Simple System for Now
Article URL: https://dannorth.net/blog/best-simple-system-for-now/ Comments URL: https://news.ycombinator.com/item?id=48775949 Points: 9 # Comments: 1
Jamesob's guide to running SOTA LLMs locally
Article URL: https://github.com/jamesob/local-llm Comments URL: https://news.ycombinator.com/item?id=48775921 Points: 16 # Comments: 2
DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation
Large Language Model (LLM)-based agents can solve complex procedural tasks by interacting with environments over multiple turns, but this ability typically depends on large models, long…
According to Bernstein, SK Hynix has 90% profit margin on dram
https://x.com/jukan05/status/2073032040451366952 https://www.google.com/search?q=bernstein+dram+report Now if we could get them down to a typical automotive profit margin of 5%, then we would have ram for our local systems…
Bridging Spherical Black-Box Optimizers
We are pleased to present our research at ICML 2026, “Bridging Spherical Black-Box Optimizers”. Full Paper: https://arxiv.org/abs/2606.25761 When optimizing through simulators, external APIs, or in reinforcement…
b9867
spec: support spec-draft-p-min in DFlash (#25246) spec: support spec-draft-p-min in DFlash dflash: add n_min guard dflash: guard both n_min and n_max macOS/iOS: macOS Apple Silicon (arm64)…
ReFreeKV: Towards Threshold-Free KV Cache Compression
To reduce memory consumption during LLM inference, a handful of methods have been proposed for KV cache pruning. While these techniques can accomplish lossless memory reduction…
Anyone tried using the new (ish) Gemma diffusion model as a speculative model?
It seems that MTP is the gold standard for speed up but still suffers from having to choose between regressive and parallel drafters that come with…
June 2026 newsletter
The June edition of my sponsors-only monthly newsletter is out. If you are a sponsor (or if you start a sponsorship now) you can access it…
Company Emmi joins Mistral to accelerate the AI-native industry May 23, 2026 Mistral AI
Company Emmi joins Mistral to accelerate the AI-native industry May 23, 2026 Mistral AI
Give Smart People the Tools to Do Smart Things
Article URL: https://superuserdone.com/posts/2026-07-03-give-smart-people-the-tools/ Comments URL: https://news.ycombinator.com/item?id=48775748 Points: 8 # Comments: 0
RT Andy Jassy: Project Hail Mary is now on Prime Video, free for Prime members everywhere. It’s my favorite movie that I've seen in a long time. Trul…
RT Andy JassyProject Hail Mary is now on Prime Video, free for Prime members everywhere.It’s my favorite movie that I've seen in a long time. Truly…
Mistral released Leanstral-1.5-119B-A6B
Leanstral 1.5, a free Apache-2.0 licensed model with 6B active parameters, delivers a major performance upgrade in formal verification, saturating miniF2F, solving 587/672 PutnamBench problems, and…
BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding
Speculative decoding accelerates inference by using a lightweight draft model to generate candidate tokens in parallel, and are then verified by the target model, enabling lossless…
Instead of banning AI, I made a classroom contract with my students
Article URL: https://www.science.org/content/article/instead-banning-ai-i-made-classroom-contract-my-students Comments URL: https://news.ycombinator.com/item?id=48775499 Points: 28 # Comments: 7
Show HN: TaskPeace – a task queue my AI coding agents pull work from over MCP
Article URL: https://taskpeace.com/ Comments URL: https://news.ycombinator.com/item?id=48775484 Points: 3 # Comments: 0
Anatomy of Persistent Memory's 3 Layers: Comparing ContextNest, Mem0 and Zep
Article URL: https://promptowl.ai/resources/persistent-memory-ai-agents/ Comments URL: https://news.ycombinator.com/item?id=48775483 Points: 4 # Comments: 0
b9866
cuda: enable topk-moe fusion for 288 experts (#25267) cuda: enable topk-moe fusion for 288 experts The topk-moe fusion only accepted power-of-2 expert counts (or the special-cased…
RT Manoj Nair: Re None of it was an accident. A team that gave up recharge week, and a partnership @GeoffBibby built with @swyx + the AI Engineer crew…
RT Manoj NairRe None of it was an accident. A team that gave up recharge week, and a partnership @GeoffBibby built with @swyx + the AI…
ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
In prefill-decode (PD) disaggregated LLM serving, each request is assigned to a decode worker after prefill. Existing decode routers balance only load; for mixture-of-experts (MoE) models…
RT Peter Gostev: I spent a LOT of time through the hardest 3D prompts at Fable, it is a 45 min video, but I have 60+ very cool demos for you. Also pro…
RT Peter GostevI spent a LOT of time through the hardest 3D prompts at Fable, it is a 45 min video, but I have 60+ very…