🌳 LSM Trees

Write Optimization, Compaction, Level Structure, RocksDB Internals

Bawdy, playful and intellectually ambitious: your guide to the 2025 Miles Franklin shortlist
theconversation.com·14h
🧩Types
How to justify your SEO budget in 2025
searchengineland.com·23h
⚡Search Latency
Dream Weapons present: WALK WITH ME IN BEAUTY C60
dreamweapons.net·21h
🏹Apache Arrow
23 jul 25 briefs
pdbowman.studio·22h
🏛️Politics
Every Thought That I Have About Clair Obscur: Expedition 33
infactuous.bearblog.dev·4h
🕳LLM Vulnerabilities
Taking Abundance Seriously
lesswrong.com·1h
🏛️Politics
Good Enough: The Real Value of AI Today
athonlab.com·20h·
Discuss: Hacker News
🏆LLM Benchmarking
Cursory Analysis of LLMs in the US Gov (July 2025)
lesswrong.com·2h
🤖AI
Clowns to the Left of Me
blog.korny.info·19h·
Discuss: Hacker News
🛡️AI Security
GhostUMAP2: Measuring and Analyzing (r,d)-Stability of UMAP
arxiv.org·7h
🐘pgvector
ICML Statement about subversive hidden LLM prompts
icml.cc·22h·
Discuss: Hacker News
🕳LLM Vulnerabilities
Can You Build Agent2Agent Communication on MCP? Yes
devblogs.microsoft.com·12h·
Discuss: Hacker News
📋MCP
Can AI Make Me Famous? My Experiment in Machine-Generated Music
hackernoon.com·5h
🎭Claude
Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs
arxiv.org·7h
🏆LLM Benchmarking
Can External Validation Tools Improve Annotation Quality for LLM-as-a-Judge?
arxiv.org·7h
🏆LLM Benchmarking
A lightweight TCP in UDP tunnel using eBPF for MPTCP
github.com·20h·
Discuss: Hacker News
⚡QUIC Protocol
Thinking Machines and the Second Wave: Why $2B Says Everything About AI's Future
decodingdiscontinuity.com·18h·
Discuss: Hacker News
🆕New AI
CQE under Epistemic Dependencies: Algorithms and Experiments (extended version)
arxiv.org·7h
🧮SMT Solvers
BetterCheck: Towards Safeguarding VLMs for Automotive Perception Systems
arxiv.org·7h
🛡️AI Safety
Agents Are Not Tools
discuss.google.dev·14h·
Discuss: Hacker News
🪄Prompt Engineering