back
user profile

matt_d

21,159karma·3,275submissions·April 21, 2014
recent activity (3,275 total)
4 pts
Benchmarking LLMs on File System Design and Implementation(arxiv.org)
7d ago·discuss
3 pts
Differential heuristics: learning about a way to optimize the A* heuristic(redblobgames.com)
7d ago·discuss
2 pts
Classifying Capabilities (Extended Version)(arxiv.org)
8d ago·discuss
1 pts
TensorLift: Auto Extraction of ISA Semantics from Accelerator RTL via MLIR(arxiv.org)
9d ago·discuss
3 pts
A Revised Haskell 2010 Language Report(blog.haskell.org)
9d ago·discuss
1 pts
User awareness in frontier models: Who's asking shifts what models say(transluce.org)
9d ago·discuss
3 pts
OBASE: Object-Based Address-Space Engineering to Improve Memory Tiering(usenix.org)
9d ago·discuss
3 pts
Domain-specific hyperspecialization: Winning the SC26 SAT track with LymphoSAT(c.mov)
9d ago·discuss
1 pts
Benchmarking the Residual: What Long-Horizon Evals Add Beyond Short-Task Perf(arxiv.org)
9d ago·discuss
2 pts
Automatically Retrofitting JIT Compilers(infoq.com)
9d ago·discuss
3 pts
tla-rs: IronFleet and AutoMan in Verus(github.com)
9d ago·discuss
1 pts
Introducing Dogwood: runtime verification for AI agents(aws.amazon.com)
9d ago·discuss
3 pts
Beyond the Library: An Agentic Framework for Autoformalizing Research Math(arxiv.org)
9d ago·discuss
1 pts
Modeling LLM Performance from First Principles(sidbabu.com)
9d ago·discuss
1 pts
LettuceDetect v2 in Semantic Router: Gen. Hallucination Detection vLLM Endpoint(vllm-sr.ai)
9d ago·discuss
1 pts
Continual Learning via Real-Time RL for Agents(rllm-project.com)
9d ago·discuss
13 pts
Smalltalk Report from 1991 to 1996(github.com)
10d ago·discuss
2 pts
The State of MPI: Current Standard and Future Plans(hpc.fau.de)
10d ago·discuss
3 pts
A Primer to ML Compilers(aramesh10.github.io)
10d ago·discuss
3 pts
Inside Kimi K3's AgentENV: Can It Really Fork in 100 ms?(gensee.ai)
11d ago·discuss
7 pts
Enabling the next iteration of the borrow checker on nightly(blog.rust-lang.org)
11d ago·discuss
2 pts
Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production(arxiv.org)
11d ago·discuss
1 pts
Certified Program Synthesis with a Multi-Modal Verifier [pdf](verse-lab.org)
12d ago·discuss
1 pts
Compiler-Grounded Hierarchical Diagnosis for LLM Triton Kernel Optimization(arxiv.org)
12d ago·discuss
1 pts
NIIN: NVSHMEM Implemented In NCCL(github.com)
12d ago·discuss
1 pts
ACM SIGOPS Symposium on Operating Systems Principles SOSP'26 Papers & Preprints(pchaigno.github.io)
13d ago·discuss
11 pts
Reliability Lessons from SQLite – Richard Hipp – SSW 2026 [video](youtube.com)
13d ago·1 comments
22 pts
Stanford CS329A: Self-Improving AI Agents(youtube.com)
13d ago·discuss
1 pts
Demystifying Deep Learning Compiler Front End Bugs: An LLM-Aided Empirical Study(arxiv.org)
13d ago·discuss
3 pts
Towards Designing an Execution Control System with Metastability Resilience(muratbuffalo.blogspot.com)
14d ago·discuss