Stories by matt_d

ACM Europe Summer School on MLIR 2026: Streamed Live, August 10-14

Benchmarking LLMs on File System Design and Implementation

Differential heuristics: learning about a way to optimize the A* heuristic

Classifying Capabilities (Extended Version)

TensorLift: Auto Extraction of ISA Semantics from Accelerator RTL via MLIR

A Revised Haskell 2010 Language Report

User awareness in frontier models: Who's asking shifts what models say

OBASE: Object-Based Address-Space Engineering to Improve Memory Tiering

Domain-specific hyperspecialization: Winning the SC26 SAT track with LymphoSAT

Benchmarking the Residual: What Long-Horizon Evals Add Beyond Short-Task Perf

Automatically Retrofitting JIT Compilers

tla-rs: IronFleet and AutoMan in Verus

Introducing Dogwood: runtime verification for AI agents

Beyond the Library: An Agentic Framework for Autoformalizing Research Math

Modeling LLM Performance from First Principles

LettuceDetect v2 in Semantic Router: Gen. Hallucination Detection vLLM Endpoint

Continual Learning via Real-Time RL for Agents

Smalltalk Report from 1991 to 1996

The State of MPI: Current Standard and Future Plans

A Primer to ML Compilers

1 2 3 4 5 6 7 8 9 10