We run scheduled news sweeps and publish only the items that clear the editorial threshold.
Notch kept its Claude Agent SDK harness and routed it to GPT-5.6 Luna through a LiteLLM proxy, cutting median harness cost per completed session from $4.44 to $0.50. The more transferable finding: models that passed the same evals still…
The authors built a coding harness from scratch around a fixed ReAct execution loop, then varied three components independently: an explicit planning step, the action interface (a curated tool set versus a bash-only shell), and context…
Posted live from a talk in Amsterdam covering "12-factor factories," SlopCodeBench, and something he called "the gas town situation"; 2,767 views and 24 likes about three hours after posting, with one reply confirming the talk took place.…
In a large search space, a fixed exploration strategy stops adapting as the space grows, while tuning the strategy online consumes a full discovery run for every policy test. Dream-RSI treats a coding agent's history, the record of what…
The survey builds a five-level autonomy framework, running from a system that executes human-specified updates to one that revises the mechanisms governing its own future improvement, and uses it to classify existing work. The Darwin…
Robinson writes that engineering teams spent the first half of 2026 handing as much work as possible to agents and got "mountains of dubious code, but no tsunami of incredible software" in return. He ranks the development environment…
The researchers tested seven models across three harnesses, Claude Code, Codex CLI, and the minimal open-source harness Pi, on SWE-bench Lite and Terminal-Bench 2.0: 21 pairs, 30 sampled tasks repeated three times each. Claude Fable 5…
On September 2, Teknium set Hermes Agent, Nous Research's open source coding agent, on a standing cleanup goal for the project's own codebase, more than a million lines of non-test Python. The main run took about nineteen active hours,…
Yegge's Wheelhouse orchestrator, the successor to his earlier Gas Town system, ran about 25 Claude Fable instances alongside 25 Opus and Sol instances at peak in August. Fuel costs kept climbing: he went from adding a Claude Max account…
Browser Use launched jev, a browser-agent tool. Dex Horthy, author of 12-Factor Agents, described its tool calling as classify-then-act stages inside pipelines that mix deterministic code with small agent loops.
OpenAI published a standing framework for tracking, investigating, and disclosing model misalignment, sorting cases into three tracks, Ready for Disclosure, Minor Investigation, and a slower Larger Investigation track, with unresolved…
Pritzker walks through a single incident from July 9, when a partner's webhook sent a burst of events that broke a database job. A Cygnet job queried Datadog on its own, found the burst, and opened a ticket with its query, the time…
Zunic traces four stages his team moved through since launching Browser Use in November 2024. First, a fixed action space of click, type, and scroll, with the harness deciding what the model could see.
Saravia quote-tweeted a post from Eric Provencher (@pvncher), who wrote: "if you're running more than 2 sub agents at time, you're almost certainly burning tokens for 0 quality gain," adding that "agents don't trust each other enough to…
Pocock posted a short rule for introducing an agent into a triage workflow: "When you first start building a software factory, make it TINY. Don't get it to triage every issue in your repo.
Gergely Orosz interviewed seven OpenAI engineers and engineering leaders, including Venkat Venkataramani, VP of Engineering for Applied Infra, about the pipeline that now runs the company's software. In Orosz's account, a human still…
Malhotra describes how Anthropic's CI job volume grew 25x over six months, driven by a codebase where the number of tests grew 10x while headcount barely moved. Engineers there now ship 8x as much code per quarter as they did between 2021…
X Article, September 15, 2026. Warp's CEO lays out a three-stage adoption path for agent-driven development and says the company's internal "walk factory" automates about 75% of changes to warp.dev.
X Article, September 15, 2026. Proposes "behavioral evaluation," discrete checks such as whether an agent asks a clarifying question or runs a validator before declaring a task done, as a complement to end-to-end benchmarks.
Amodei's case rests on two developments. First, he writes that "since roughly this summer, AI has been advancing drastically faster, driven primarily by AI's growing ability to build the next generation of AI," a dynamic he says is…