Related reading
Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem
The authors cast transformer block removal as a constrained binary optimization problem equivalent to an Ising glass, using a Hessian‑derived energy as a proxy for downstream quality. Solving the resulting QUBO with classical or quantum‑inspired solvers yields up to 23 MMLU points improvement over prior block‑removal baselines at 50 % depth compression.
Hugging Facehuggingface.co8 minTSMC revealing details about next gen A14 node
TSMC’s upcoming A14 NanoFlex Pro node promises the world’s smallest SRAM cell (<0.017 µm²) and up to 30% power savings, with a 10‑15% speed boost and ~20% density increase over N2. The platform also introduces TSV and RDL innovations for 4.5 µm SoIC bonding, targeting volume production in 2028.
Hacker News front pagemapyourshow.com1 mintalkHN12455Bun Rewrites 535K Lines of Zig into Rust in Four Months, Eliminates Numerous Memory Leaks
Bun, the JavaScript runtime, rewrote its 535K lines of Zig code into Rust in four months using an AI-orchestrated process. This eliminated numerous memory leaks and improved performance, achieving a task estimated to take human engineers a year.
InfoQinfoq.com4 minGAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning
GAVEL augments LLM‑driven robot planners with an explicit graph world model that verifies actions, repairs violations, and reasons over belief distributions, boosting single‑task success from 41 % to 92 % and multi‑task success from 20 % to 93 % on BEHAVIOR‑1K.
Hugging Face Daily Papersarxiv.org1 minpaperDropbox Outlines How Focusing on Existing Infrastructure Efficiency Can Create Headroom for AI
Dropbox details how a decade‑long program of infrastructure efficiency—forecasting, deep‑sleep servers, workload rebalancing, higher‑density storage, reliability‑based hardware refresh, and rack‑level power upgrades—has cut storage power use by >50% and created headroom for AI workloads without new data‑center builds.
InfoQinfoq.com2 minSamsung is expected to more than double output of its HBM4 and HBM4E DRAM
Samsung plans to more than double its HBM4 and HBM4E output next year, raising glass‑carrier cleaning to 50 k sheets/month and wafer input to ~250 k per month. The HBM4 family’s share of shipments is expected to jump from ~40 % to ~80 % as the higher‑layer HBM4E ramps up.
Hacker News front pagesedaily.com2 minHN547444
