---
title: 'In the News: October 17, 2026 (Morning)'
description: "Orbital Witness's CTO reports merged PRs per engineer roughly doubled after a harness rebuild, and grades the team against OpenAI's twelve theses."
canonical_url: 'https://darkfactory.dev/news/2026-10-17-morning'
markdown_url: 'https://darkfactory.dev/news/2026-10-17-morning.md'
collection: news
date_published: '2026-10-17T07:25:00-04:00'
date_modified: '2026-10-17T07:25:00-04:00'
---

# In the News: October 17, 2026 (Morning)


One company has published its own scorecard against OpenAI's harness engineering playbook, with throughput figures and a list of what it has not built. The numbers are self-reported and the post doubles as a hiring pitch, but it is a first-hand account of a production harness.

## 1. Orbital Witness reports merged PRs per engineer roughly doubled after a harness rebuild, and marks three of twelve theses as half-built

**[Grading Ourselves Against the Harness Engineering Playbook](https://tech.orbitalwitness.com/posts/2026-07-22-grading-ourselves-against-the-harness-engineering-playbook/)** · Andrew Thompson, CTO, Orbital Witness · Orbital's Tech Blog, July 22, 2026

Thompson scores his team's harness against the twelve theses in Ryan Lopopolo's harness-engineering repository, the follow-up to OpenAI's February post on shipping with Codex. He reports that on a legacy codebase with the harness switched on, weekly merged PRs per contributor rose from about 3 to the mid-to-high single digits, mostly 6 to 7. On a newer codebase built fully around the harness he reports a swing between the low teens and low twenties a week, about three times the legacy repo's rate. He says every PR clears the same review, type-check and CI gates as before, with agents handling most review and humans checking the rest. He gives these as ranges, and merged PRs are a proxy for output, not a measure of it.

The harness pieces he describes are specific: an isolated Docker stack per worktree so agents run the real system, a nightly bug hunt in which sceptic agents try to refute each finding before a fix is attempted, forbidden paths re-checked on every push to an agent-authored PR, human-only merges, and a git hook that stamps each agent-assisted commit with token and dollar cost. He marks three theses as only partly built: turning feedback into infrastructure, retiring nightly loops that have no end condition, and measuring effectiveness. On the last he writes that "we measure cost, not attention."

**Why it matters:** The gaps are the useful part. A team running a mature harness says it can price a commit in tokens but cannot yet measure the steering and review time a commit costs a human, which is the metric the playbook says matters. Treat the PR figures as one team's self-report, and the unbuilt list as a checklist for your own harness.

---

## Also this cycle

- **[DeepSeek-V4.1-Flash-1017](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017)** · DeepSeek-AI · Hugging Face model card · MIT-licensed open weights with a 1M-token context window. DeepSeek reports 42.3 on Terminal-Bench 4.0 using the Claude Code harness, up from 31.2 for the previous Flash release. These are the vendor's own figures, not independently reproduced.