BLOG
DeepSeek Harness proposes a Super-agent built from a long-lived Router, isolated Workers, event Triggers, durable state, and an external Watchdog.
Stanford's Paper2Agent turns papers, code and data into tested MCP tools, then measures reproducibility, new-query accuracy and cross-paper discovery while keeping humans in the loop.
Shopify built Remote Dev to move iOS and Android builds, simulators and verification off laptops, so River agents can run mobile work in parallel; River's share of merged mobile PRs rose from 6% to 61%.
System One models skip token-by-token answers and return a choice, score, or probability in one forward pass. A guide to 15 studies on dynamic candidates, multimodality, retrieval, and selective reasoning.
Mirendil-Base, the first pretrained coding model built by one researcher with agents in 3.5 months and under $10M compute, beats several 100B+ MoE bases on held-out code bits per byte.
Observability answers what happened; the real cost lives in what follows. A four-layer self-repairing stack: tracing, Ollie's patch loop, regression-locking test suites, and an agent sandbox.
With Claude writing about 90 percent of Claude Code, Anthropic runs seven layers of automated review plus risk-tiered approval, doubling merged PRs while reverts fell 40 percent. The most instructive finding is convergence: an agent author and agent reviewer once burned fifty-plus rounds on one PR, and git blame showed 59 percent of the repeatedly flagged code had been there since the first pass.
Gergely Orosz visits OpenAI: Codex and ChatGPT Work have taken over everything; a nine-step agentic software factory with Perf Factory and Sevbot, and the rethink of IDEs and pull requests.
Meta distills compliance expertise into 200+ structured files, splits what the agent knows from how it reasons via recipes, and compiles expert fixes into regression-tested edits, no model retraining.
A source-code grounded walkthrough of GPT-6 Astra: accessibility trees instead of pixel guessing, a persistent Node REPL, actions written as code, and a Guardian policy that blocks risky operations before execution.
MHS uses standardized drivers, read/write primitives, natural-language machine descriptions, and MCP/CLI/API control to connect heterogeneous lab and manufacturing equipment to AI agents. The preview includes AWS, Doosan, Universal Robots, Tecan, QIAGEN and others, while emphasizing expert oversight for physical reasoning and safety.
As an Amazon Associate, we earn from qualifying purchases.
