HNHacker News
TopNewBestAskShowJobs

matt_d

22,537 karma · joined April 21, 2014

submissionscomments

NCMNext-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation

scalingintelligence.stanford.edu·2 pts·matt_d·
0

Apples to Apples: Getting Type Mappings Right in LLM-Based Code Translation

codemetal.ai·8 pts·matt_d·
0

Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Agents

arxiv.org·6 pts·matt_d·
0

Heterogeneity in AI: Pathways from Inference to Compound Systems (Dissertation)

doi.org·2 pts·matt_d·
0

Haskell: Origins, evolution, and future – Peyton Jones – JuliaCon Global 2026 [video]

youtube.com·2 pts·matt_d·
0

High-Level Algebra for Low-Level Tensor Optimization in ATL

stng.substack.com·1 pts·matt_d·
0

Rolling Round-Robin Rate: Standard Heterogeneous Throughput for SPEC CPU

arxiv.org·1 pts·matt_d·
0

To Classify, Try a Trie Tree

fsdatalab.github.io·4 pts·matt_d·
0

Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents

arxiv.org·5 pts·matt_d·
0

Stateless Language Agents: Scaling Long-Horizon Automated Research

arxiv.org·3 pts·matt_d·
0

Empirical Computation: Prompting versus Programming [pdf]

mboehme.github.io·1 pts·matt_d·
0

Retrofitting language models to operate over bytes

nature.com·2 pts·matt_d·
0

VibeSys Builds a Qwen3.5-397B Engine on MI300A, 2.3× Tuned SGLang

syfi.cs.washington.edu·2 pts·matt_d·
0

GitSwarm: Decentralized Compounding Inference

veds12.github.io·2 pts·matt_d·
0

What mathematicians should know about the Lean Theorem Prover: reliability & AI

terrytao.wordpress.com·210 pts·matt_d·
58

Ahead-of-Time Compilation of JavaScript to WebAssembly via Static Type Inference [video]

vimeo.com·1 pts·matt_d·
0

A Self-Pruning Transformer: Extreme KV-Cache Compression w/Universal Attention

arxiv.org·6 pts·matt_d·
0

Bitmaps in the Linux Kernel

0xax.dev·12 pts·matt_d·
6

Equality Saturation: An "Incomplete" Project

blog.sigplan.org·1 pts·matt_d·
0

Vosti: Specifying, Implementing, and Verifying Deterministic LLM Inference

arxiv.org·1 pts·matt_d·
0

Agent Plasticity: Measuring Self-Improvement Through Experience

harmandotpy.github.io·4 pts·matt_d·
0

DeLM: Decentralized Multi-Agent Systems with Shared Context

yuzhenmao.github.io·4 pts·matt_d·
0

Towards Efficient HPC Systems for Agents: Challenges and Opportunities

arxiv.org·1 pts·matt_d·
0

ServeLearnBench: How Well Can Agents Self-Improve from Serving Experience?

infini-ai-lab.github.io·1 pts·matt_d·
0

Slot Machine Programming and the Hidden Curriculum

thelastsoftwareengineer.substack.com·2 pts·matt_d·
0

Jev-Driven SRE Diagnosis: What Worked and What Failed

sregym.com·50 pts·matt_d·
27

Flow Typing: A New Lens on Linearity [pdf]

people.cs.nott.ac.uk·4 pts·matt_d·
0

Proof-Carrying-BPF Programs for the eBPF Verifier

al.radbox.org·1 pts·matt_d·
0

Sentry: Learning to Recover from LLM Agent Failures at Test Time

github.com·1 pts·matt_d·
0

KCoral: Lightweight Benchmark Server for Agentic GPU Programming

blog.mlc.ai·1 pts·matt_d·
0
← PreviousPage 5 of 34Next →