Live feed

github.com · 2026-11-02 · Ranked: agent match · community signal · fresh 1.00 · score 3.32 · Context

Show HN: AgentTM – A time-travel debugger for AI coding agents built in Go

developer.nvidia.com · 2026-11-02 · Ranked: community signal · fresh 0.93 · score 3.04 · Context

Optimizing 124B MoE inference on a single Nvidia DGX Spark

github.com · 2026-11-02 · Ranked: community signal · fresh 0.97 · score 2.78 · Context

Show HN: Shipvo – open-source RN OTA updates and an AI-drivable simulator

arxiv.org · 2026-10-30 · Ranked: evaluation match · research watch · fresh 0.69 · score 2.13

From Training Exposure to Membership Evidence: A Controlled Study of OLMo 2

Whether a language model was trained on a document matters for copyright, privacy, and benchmark contamination. Yet most membership-inference (MI) evaluations on language models collect members and non-members after t... Context & related coverage →

arxiv.org · 2026-10-30 · Ranked: eval match · research watch · fresh 0.69 · score 2.08

Peeling the Matryoshka: Extracting Ontological Structure from Retrieval Embeddings

Taxonomy construction is essential for knowledge-intensive NLP yet remains costly: clustering-based methods (i) need careful per-corpus tuning and yield unstable hierarchies, while LLM-based pipelines (ii) depend on e... Context & related coverage →

arxiv.org · 2026-10-30 · Ranked: agent match · research watch · fresh 0.69 · score 2.06

RECAST: REconstruction of Chain-of-Thought via Auditable Structured Traces

Large closed-source reasoning models expose only their final answers. The intermediate reasoning that produces those answers is hidden behind API surfaces, tool-call policies, and safety filters. Existing chain-of-tho... Context & related coverage →

arxiv.org · 2026-10-30 · Ranked: evaluation match · research watch · fresh 0.70 · score 2.03

When Does Test-Time Search Help World Action Models? An Empirical Audit of Candidate Selection and Simulator Integrity

World-action models increasingly apply test-time scaling, spending extra inference computation on candidate selection and adaptive allocation to improve control. Such gains are credible only when candidates carry expl... Context & related coverage →

arxiv.org · 2026-10-30 · Ranked: research watch · fresh 0.70 · score 1.96

There Is No Free Loop: When Does Looping a Trained Model Pay for Its Inference Compute?

Looping re-applies a block of layers so that each token passes through the block more than once. Adding a loop to a trained model is attractive because it leaves the parameter count, and hence the disk size, the memor... Context & related coverage →

simonwillison.net · 2026-10-30 · Ranked: practitioner analysis · fresh 0.60 · score 1.67

dbreunig/nesformer

dbreunig/nesformer Inspired by qwenputer by Divyansh Agrawal, Drew Breunig baked a working emulator for a Nintendo Entertainment System 6502 CPU into the weights of Qwen3.5-4B. You can now play NES ROMs such as Super... Context & related coverage →

newsletter.semianalysis.com · 2026-11-02 · Ranked: practitioner analysis · fresh 0.93 · score 1.65

GDPx: Measuring Frontier Model Capabilities Across the Most Valuable Domains

A frontier benchmark spanning RSI, hardware design, cyber, bio, finance, legal, quant trading, chip design, software engineering, materials science, and alignment Context & related coverage →

cloud.google.com · 2026-10-30 · Ranked: agent match · cloud platform update · fresh 0.46 · score 0.95

Innovate on your own business terms: Google Cloud spend caps now generally available

Today, we’re announcing that spend caps on Google Cloud Budgets are generally available. With this release, we’re delivering ways to protect your workloads from runaway costs without risking resource deletion. More im... Context & related coverage →