Fungus: The Befunge CPU(2015)
⚙️Mechanical Sympathy
Flag this post
StreetMath: Study of LLMs' Approximation Behaviors
arxiv.org·23h
🏆LLM Benchmarking
Flag this post
How Distributed ACID Transactions Work in TiDB
pingcap.com·11h
🏗️FoundationDB
Flag this post
Your Transformer is Secretly an EOT Solver
🧠LLM Inference
Flag this post
Rearchitecting Vector Search: A Migration from MongoDB Atlas to Qdrant
pub.towardsai.net·20h
🎯Qdrant
Flag this post
2025 Holiday Readiness Checklist (Page Speed Edition!)
speedcurve.com·2h
🚀Web Performance
Flag this post
Reflection for Aggregates (2020)
🦀Rust Compiler Internals
Flag this post
Context Engineering: The Foundation for Reliable AI Agents
thenewstack.io·7h
🪄Prompt Engineering
Flag this post
🎲 On LLMs
kaukas.mataroa.blog·18h
🪄Prompt Engineering
Flag this post
Anyone else running their whole AI stack as Proxmox LXC containers? Im currently using Open WebUI as front-end, LiteLLM as a router and A vLLM container per mod...
🏗️LLM Infrastructure
Flag this post
Accelerating AI inferencing with external KV Cache on Managed Lustre
cloud.google.com·11h
🏗️LLM Infrastructure
Flag this post
My first fifteen compilers (2019)
💻Programming languages
Flag this post
original ↗
jvt.me·3h
🏝️Islands Architecture
Flag this post
Turbo: Just another AUR helper.
🦀Rust Compiler Internals
Flag this post
Introducing Project Telos: Modeling, Measuring, and Intervening on Goal-directed Behavior in AI Systems
lesswrong.com·18h
🛡️AI Safety
Flag this post
We’re back with episode 2 of 1 IDEA! Today, Vinay Perneti (VP of Eng @ Augment Code) shares his own Bottleneck Test
🧭Content Discovery
Flag this post
From Lossy to Lossless Reasoning
🔤Tokenization
Flag this post
Loading...Loading more...