matt_d | Dark Hacker News

user:	matt_d
created:	April 21, 2014
karma:	20.4k

1.	Senior SWE-Bench: open-source benchmark that assesses agents as senior engineers(senior-swe-bench.snorkel.ai) 145 points by matt_d 15 hours ago \| 98 comments
2.	Software Security Analysis in 2030 and Beyond: A Research Roadmap(dl.acm.org) 2 points by matt_d 21 hours ago \| 0 comments
3.	VeriCache: Turning Lossy KV Cache into Lossless LLM Inference(arxiv.org) 1 points by matt_d 21 hours ago \| 0 comments
4.	Designing GPU-Accelerated Query Engines with NVIDIA GQE(developer.nvidia.com) 1 points by matt_d 22 hours ago \| 0 comments
5.	Teaching Algorithms in 2026(cs.uni.edu) 2 points by matt_d 1 day ago \| 0 comments
6.	Pragmatic Approaches to Improving Compiler Correctness(2026.ecoop.org) 1 points by matt_d 1 day ago \| 0 comments
7.	The Expensive Fictions of Low-Level Programming Languages(stng.substack.com) 1 points by matt_d 1 day ago \| 0 comments
8.	On the Efficacy of PyTorch for High-Performance Computing(dl.acm.org) 2 points by matt_d 1 day ago \| 0 comments
9.	Accelerating LLM Inference on AMD GPUs with Low-Latency GEMMs(rocm.blogs.amd.com) 2 points by matt_d 1 day ago \| 0 comments
10.	Agentic Hardware Design as Repository-Level Code Evolution(arxiv.org) 1 points by matt_d 1 day ago \| 0 comments
11.	Reward hacking is swamping model intelligence gains(cursor.com) 3 points by matt_d 2 days ago \| 0 comments
12.	Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity(microsoft.com) 6 points by matt_d 2 days ago \| 0 comments
13.	Compiler-Assisted Floating-Point Error Analysis and Profiling with FPChecker(fpanalysistools.org) 30 points by matt_d 2 days ago \| 6 comments
14.	Are We Ready for an Agent-Native Memory System?(arxiv.org) 2 points by matt_d 3 days ago \| 0 comments
15.	Micro-Agent: Beat Frontier Models with Collaboration Inside Model API(vllm.ai) 80 points by matt_d 3 days ago \| 22 comments
16.	TraceLab: Characterizing Coding Agent Workloads for LLM Serving(syfi.cs.washington.edu) 1 points by matt_d 3 days ago \| 0 comments
17.	It's Always the Learning Rates(ianbarber.blog) 2 points by matt_d 3 days ago \| 0 comments
18.	Efficiency in LLMs – Part 1 – Columbia Machine Learning Summer School 2026 [video](youtube.com) 5 points by matt_d 3 days ago \| 0 comments
19.	Using Local Coding Agents(magazine.sebastianraschka.com) 3 points by matt_d 4 days ago \| 0 comments
20.	The Thing We All Obviously Want(kmicinski.com) 3 points by matt_d 5 days ago \| 0 comments
21.	ActPlane: Programmable OS-Level Policy Enforcement for Agent Harnesses(arxiv.org) 8 points by matt_d 6 days ago \| 1 comment
22.	Fenwick trees for products mod 2ⁿ(bitmath.blogspot.com) 1 points by matt_d 6 days ago \| 0 comments
23.	A Fake Shell for Pangenomics(cs.cornell.edu) 36 points by matt_d 6 days ago \| 5 comments
24.	Making Equality Saturation Usable for Developing Vectorized Compilers(dl.acm.org) 1 points by matt_d 6 days ago \| 0 comments
25.	Reading AI Model Compilation in MLIR Through the Lens of Formal Theories(arxiv.org) 2 points by matt_d 6 days ago \| 0 comments
26.	Liveness Proofs in Veil, Part I: The First Step(proofsandintuitions.net) 2 points by matt_d 6 days ago \| 0 comments
27.	ParallelKernelBench: Can LLMs write fast multi-GPU kernels?(github.com) 3 points by matt_d 7 days ago \| 0 comments
28.	LXM: Better Splittable Pseudorandom Number Generators (and Almost as Fast) [video](youtube.com) 2 points by matt_d 7 days ago \| 0 comments