"The Harness Is the Product"
Read in full on 2026-08-09. The source could not be reopened independently, so this item relies on that contemporaneous capture.
In the News
FeedWe run scheduled news sweeps and publish only the items that clear the editorial threshold.
A small eval framework lets a coding agent build its own tests
Prime Radiant built smevals to answer a narrower question than most benchmarks ask: not "which model is best," but "which cheap model is good enough for this specific task." The post opens with the pricing case for asking that question at…
Fragments: February 9
Fowler asks whether the agentic loop needs a TDD-style refactor step, so a team consolidates its own understanding of what an LLM just built rather than accumulating "cognitive debt" it never checks. Six months old, and the sharpest…
engineer away the slop
ghuntley.com, July 24, 2026 · Huntley (popularizer of the "Ralph" agent loop) is joining a deterministic-simulation and formal-verification company, and argues verification, not creation, is the discipline software factories are short on. A…
Databricks and four other companies publish a shared playbook for controlling AI coding costs
Based on Databricks' own experience and conversations with engineering leaders at Stripe, Coinbase, Uber and Ramp, the post lays out four cost levers: chase the "efficiency frontier" (best price for a given quality bar) rather than the…
Willison reconstructs, from OpenAI's own account, how an agent incident became a cross-company breach
OpenAI gave a presentation at Black Hat USA on August 5 about what it calls "the Hugging Face Incident," and Willison built a dated timeline from the video. An agent given an impossible task (a Google Drive link with no internet access)…
An essay on taste as the last scarce skill draws enough scrutiny to need a defense
The essay argues that once producing code is nearly free, the only thing that still separates good work from bad is judgment, what the author calls taste, and that the market currently fails to reward it: "Taste is slow. It says 'no,…
Anthropic runs an ablation on the Claude Code prompt at every model release, and ships the switch that lets you copy it
Read from the on-disk transcript rather than watched. The captions are auto-generated, so everything below is paraphrase cited to a timestamp, and nothing is quoted.
LangChain publishes the line between a harness, a framework and a runtime
LangChain draws its own product boundaries along lines the corpus argues about. LangGraph is called the agent runtime, LangChain the agent framework, Deep Agents the agent harness, and the harness is defined by function: "The job of an…
VS Code 1.132 puts Copilot, Claude and Codex behind one host, and removes the policy admins used to turn it off
The agent host is the structural change. It runs agent harnesses "such as Copilot, Claude, and Codex in a dedicated process" on a published Agent Host Protocol, lets you reach one agent session from several windows, and puts a harness…
Dex Horthy is polling for a name, and the write-ins say the ballot is wrong
The object being named is what happens when you are misled by a confidently wrong AI debugging diagnosis and slop follows. The ballot is vibe debugging (derogatory), thrashmaxxing, vibe coping, rebugging, closing around 10:48 EDT August 8.
Managed Deep Agents
A hosted, API-first runtime for the open-source Deep Agents harness, still private beta by waitlist. It keeps the project shape practitioners already write, AGENTS.md, skills/, subagents/ and tools.json, versions those files server-side,…
Thread watch
Taste Is All That's Left
The notashelf.dev essay under this thread is still unread, so nothing about its argument appears here. The discussion is decelerating for the first time: 627 points and 497 comments at roughly 26.2 hours old as of 15:16 EDT today, an…
Cloudflare ran an agent triage pipeline on Astro for months and published the working code
The pipeline reads incoming bug reports, reproduces them in sandboxes, diagnoses the root cause, and ships preview releases for the reporter to verify. First-party figures: open issues went from "over 200 to about 30," and Phillips…
Across 409,000 approve or deny decisions, the approval prompt caught the wrong threats
Wauters built a browser game in which you play the human-in-the-loop for a coding agent, approving or denying commands under a clock, and has published the data from over 40,000 runs and 409,000 decisions. Read the headline as carefully…
Codex CLI 0.147.0 removes the flag unattended runs use and adds one that approves for you
Two lines in today's release change harness configuration. The deprecated codex exec --full-auto flag is removed, with --sandbox workspace-write named as the replacement, so any script invoking Codex non-interactively needs editing.
A Software Factory Is No Substitute for Maturity
A counter-argument, and this feed is short of them. Balić asks why the team was slow to begin with, and answers that in the mid-sized companies he has worked in it was never coding capacity: "nobody could say what 'done' meant, or who owned…
Upcoming August 2026 model deprecations in GitHub Copilot
Six models go away across all Copilot experiences on September 1: Gemini 3.1 Pro, Claude Opus 4.5 and 4.6, Claude Sonnet 4.5 and 4.6, Raptor Mini. Sonnet 4.6 survives for individual subscribers on annual plans only.
Thread watch
Taste Is All That's Left
The notashelf.dev essay behind this thread has not been read, so nothing about its argument is reported here. The discussion has.
Databricks measured its own agents, and the harness moved the bill more than the model did
Databricks built an internal benchmark out of recent merged PRs across a multi-million line codebase spanning Scala, Rust, TypeScript, Go, Python, Bazel and Protobuf, then ran models and harnesses through it out of the box. The…