Dynamic agent harnesses let language models change the software that shapes their own execution. This flexibility brings a new reasoning burden: a local plugin change can propagate through dependencies and cleanup. We... Context & related coverage →
Editor’s note : Want to keep up with the latest from Google Cloud? Check back here for a monthly recap of our latest updates, announcements, resources, events, learning opportunities, and more. This month, we focused... Context & related coverage →
arxiv.org · 2026-09-01 · Ranked: eval match · research watch · fresh 0.90 · score 2.39
Encoder-only Transformers remain effective for discriminative and representation-learning tasks, yet Polish encoders still largely rely on BERT/RoBERTa-style architectures. We introduce \textbf{Polish ModernBERT}, a f... Context & related coverage →
arxiv.org · 2026-09-01 · Ranked: agentic + eval match · research watch · fresh 0.90 · score 2.33
Many production systems can assess a configuration only by using it on live requests and observing noisy feedback. Modern agentic systems are a prominent example, with inference-time choices such as model selection, r... Context & related coverage →
arxiv.org · 2026-09-01 · Ranked: agent + eval match · research watch · fresh 0.91 · score 2.31
A long-horizon agent's trace outgrows both of its consumers: the human observer monitoring the run, and the agent itself, whose bounded context the trace must be folded back into. We present a live trace model, an app... Context & related coverage →
I was poking around in my ~/.cache/ folder using OmniDiskSweeper when I spotted something interesting. The OpenAI Codex desktop app (since rebranded to just ChatGPT) has 1.7GB of stuff in there in a folder called code... Context & related coverage →
simonwillison.net · 2026-09-01 · Ranked: claude code match · practitioner analysis · fresh 0.87 · score 2.17
Tool: GeoJSON Map Viewer I was helping Natalie gather some maps of local political boundaries (for the Granada Community Services District and the Midcoast Community Council ) and found a need to display some GeoJSON... Context & related coverage →
Business Wire · 2026-09-02 · Ranked: agent match · community signal · fresh 1.00 · score 2.10 · Context
Frontier coding agents can compose shell workflows that replace entire catalogs of file tools. Here is what changes when Bash becomes the primary execution interface. Context & related coverage →