--- title: 'In the News: August 3, 2026' description: 'David Crawshaw names the nightly upstream rebase as a harness primitive, and closed-source agents as the wall it hits.' canonical_url: 'https://darkfactory.dev/news/2026-08-03-evening' markdown_url: 'https://darkfactory.dev/news/2026-08-03-evening.md' collection: news date_published: '2026-08-03T20:30:00-04:00' date_modified: '2026-08-03T20:30:00-04:00' --- # In the News: August 3, 2026 David Crawshaw explains why a closed-source agent cannot be personalized and proposes a nightly upstream rebase as a harness primitive. Epoch AI's leaderboard puts a number on how large a program an agent can rebuild unaided, while StrongDM has published no factory results in two months. ## 1. A nightly cron job that rebases your fork is now a harness primitive **[Devtools must be open source](https://blog.exe.dev/devtools-must-be-open-source)** · David Crawshaw, exe.dev · exe.dev blog, 2026-08-02 Crawshaw gives two prompts for personalizing software with an agent. The first forks it. The second keeps the fork current: *"Set up a nightly cron job that executes the prompt: fetch upstream changes to the `` and rebase all local changes on top of upstream. Check that the software works as intended and replace the current version."* Agents make forking cheap to start and, for the first time, cheap to keep. Both prompts ship as a skill inside his own agent, Shelley, so the harness maintains its own modifications, and he draws a structural conclusion: *"The source code is the extension system."* Plugin systems and config files existed because learning a codebase was expensive, and it is not any more. The piece closes by naming where the technique stops: *"Where you would hit a wall, however, is Claude Code. It is closed-source software, so you don't get to personalize it."* Crawshaw also describes what part of code review still binds after twenty years of doing it: *"Over the past six months, I have discovered I don't need to read for edge cases like that any more: models are far more diligent than humans at rote correctness. Their errors are isolated to architecture, unexpected use cases, visual output their test environment is not feeding back to them, etc."* Nothing is measured, and every worked example is his own product. **Why it matters:** The nightly agent-driven rebase supplies a concrete answer to the maintenance half of the build-versus-buy question. It also turns a closed-source agent from a preference into a ceiling, which is a tool-selection decision a lot of teams are making this month. ## 2. Epoch's leaderboard puts a price on autonomous project size **[MirrorCode: What's the largest software project AI can complete on its own?](https://epoch.ai/MirrorCode)** · Tom Adamczewski, David Owen and David Rein, Epoch AI, with METR · epoch.ai, dated 2026-06-26 MirrorCode asks a model to reimplement a whole program from a compiled binary, documentation and example inputs and outputs, with no internet, no original source, and held-out end-to-end tests. Twenty-five targets include Unix utilities, interpreters and compression software. The scale figures are first-party: Claude Opus 4.7 reimplemented gotree, a bioinformatics toolkit of roughly 16,000 lines of Go with 40 or more commands, in 14 hours for $251, against Epoch's estimate that an unassisted human engineer would need 2 to 17 weeks. One of the largest tasks *"cost $2,600 for a single run and involved AI working for 19 days without human intervention."* The leaderboard, which Epoch says it updates regularly, reports Claude Fable 5 at 64 percent, GPT-5.6 Sol at 20, GPT-5.4 at 16 and GPT-5.5 at 10, on 15 medium and large programs in two languages, three runs each, 10 billion tokens per attempt. Epoch's footnote says those scores are not directly comparable with the paper's, and the page carries a June date while the leaderboard now contains a model that postdates it, so the update is real but undated. Epoch states the contamination risk itself: targets are open-source programs the models likely saw in pretraining, and *"we cannot rule out the possibility that memorization contributes to AI performance."* The scaffold and 22 of the 25 targets are released. **Why it matters:** Previous dark-factory claims in this feed have come from first-person accounts or vendor theses. Epoch's measurements put a bound on unaided project scale and attach a dollar figure to it. A 64 to 20 percent spread between the top two models on week-scale work is far wider than short-task benchmarks report, and it is the number to argue with. ## 3. The factory everyone cites has been quiet for two months **[Weather Report](https://factory.strongdm.ai/weather-report)** · StrongDM Software Factory · factory.strongdm.ai, read 2026-08-03 StrongDM's software factory is the canonical existence proof for non-interactive development: specs and scenarios in, agents write and test, no human reviews code. Its Weather Report is the most frequently updated page on that site, describing itself as *"What models we're running today, how they're configured, and what role each one plays in the factory."* The most recent entry in its log is dated **June 4th, 2026**. Two months on, the page is still a model roster and a set of parameter defaults: gpt-5.5 across the OpenAI text and code defaults, opus-4.8 for frontend aesthetics at max thinking, a consensus pair for sprint planning. The one evaluative line is about cost, not output: *"Opus 4.8 is good when you need input from another model, but I would not daily drive anything with it right now; it burns too many tokens."* The narrative pages have not moved since February. This is an absence and is reported as one: StrongDM has published no outcome data, throughput figure or defect rate at any point. **Why it matters:** If you are citing StrongDM as evidence that lights-out production works, you are citing a model-configuration table and a February essay. That is worth knowing before you put it in a deck. ## 4. A harness deliberately de-automated, with the cost stated **[Prevent cognitive debt by manually retyping LLM-generated code](https://ankursethi.com/blog/prevent-cognitive-debt-by-manually-retyping-llm-generated-code/)** · Ankur Sethi · ankursethi.com, 2026-08-02 Sethi puts a block in every agents file on his personal projects forbidding the assistant to *"create, edit, move, rename, or delete project files"* or run any state-changing command, requiring it instead to *"show me every proposed edit in the chat so I can type it in manually."* He then types the code in himself. The stated cost is his own: *"Instead of being 10x faster, I'm probably only 2x faster."* What he says he buys is a spatial map of the codebase and enough friction to catch hallucinations before they land. He names the pattern he is refusing in one line: *"Robots raise PRs, humans review them. It's a brave new world."* The scope is narrow and he says so, personal projects only, and he would only *"grudgingly"* do this for an employer. There is no measurement in the piece; the 2x and 10x are impressions. **Why it matters:** The copy-pasteable instruction block provides a concrete counterexample to the lights-out thesis. It is also the second artifact in two days prescribing human re-production as the control for cognitive debt. --- ## Also this cycle - **[Launch HN: Hoplite (YC S26)](https://news.ycombinator.com/item?id=49157997)** · Hacker News · A vendor stating the build-versus-buy decision out loud: *"We spent a lot of time deciding on whether we should use an off the shelf solution like Codex/Claude Code, but ultimately wanted the independence and freedom that came with building it in house."* Reads directly against item 1. - **[Show HN: Armature (YC P26)](https://news.ycombinator.com/item?id=49157807)** · Hacker News · Analytics and evals for agent sessions, and unusually for a Show HN it reports a measurement: *"the exact same success rate as without our instrumentation (89.17 % vs 89.15 % pass rate out of 870 runs)"*. Its named failure mode is worth the click: small models hallucinating audience IDs so a campaign goes to every contact by default.