November 2025. Anthropic published a paper. 21 researchers. A pretrained model. A straightforward experiment: teach the model to game its own training environments, then see whether the bad behaviour stays local. It didn’t. The paper, “Natural Emergent Misalignment from Reward Hacking in Production RL,” describes what happened when a model learned to exploit Anthropic’s own production coding environments and then […]
TL;DR Key Findings Text (LLM outputs) Images Video Documents / PDFs Web pages / HTML Cross-cutting: interoperability & standards Legislation & regulation Limitations, circumvention, criticism Details 1. Text watermarking — the state of play The dominant academic technique is the Kirchenbauer et al. (2023, University of Maryland) “green-list/red-list” scheme: at each generation step a hash of prior tokens pseudo-randomly partitions […]
The forged certificate problem is coming for AI content provenance too In February 2026, a judge at Southwark Crown Court sentenced Jose Alejandro Zamora Yrala to 4 years and 8 months in prison. Between January 2019 and July 2023, working alone from a home office in Surrey, he forged airworthiness certificates for more than 60,000 aircraft engine parts, most of […]
Every signed provenance claim, from a code-signing certificate to a C2PA manifest to a proposed “proof of human” credential, is only ever as trustworthy as the weakest check performed at the moment someone was allowed to start signing. This document formalises that observation into something you can audit a system against: six pillars, a five-level maturity model, the objections worth […]
On 17 January 2001, California declared a state of emergency and started rolling blackouts across the state. Wholesale electricity prices had climbed from an average of $45 per megawatt hour to over $1,400 in under a year. The state’s grid had 45 gigawatts of installed capacity against 28 gigawatts of demand at the height of the blackouts: there was more […]
The 2026 Lovable security incident represents a defining moment for the “vibe coding” ecosystem. The timeline, root causes, and subsequent fallout highlight the critical tensions between rapid, AI-driven development and traditional security practices. timeline of the incident Technical Analysis of the Vulnerability The Broken Object-Level Authorization (BOLA) Flaw The core vulnerability was a classic Broken Object-Level Authorization (BOLA) flaw. In […]
On the evening of 27 January 1986, Roger Boisjoly spread his data across a table in a teleconference room at Morton Thiokol and made his case. The O-rings that sealed the joints of Challenger’s solid rocket boosters had never been tested below 53°F. The forecast for the next morning: 29°F. The correlation between cold and O-ring damage was unmistakable in […]
A Practitioner’s Reference for Warning Lifecycle Management in Platform Engineering Version: 1.0Author: Bola OgunlanaClassification: Original framework, Cockpit to Cloud seriesOrigin: Derived from post-mortem analysis of the 1995 Sampoong Department Store collapse, mapped to persistent warning failure modes in cloud and platform engineering operations What SIGNAL Is SIGNAL is a 6-principle operational framework for managing persistent warnings in platform engineering, DevSecOps, […]
On 29 June 1995, at 5:52 PM, the Sampoong Department Store in Seoul collapsed in under 20 seconds. 502 people died. 937 were injured. South Korean prosecutors launched a criminal investigation. What they found wasn’t a building that gave no warning. It was a building that sent warnings for three months and had every one of them ignored. Platform engineering […]
On 27 March 1977, two Boeing 747s collided on a single runway at Los Rodeos airport in Tenerife. Fog had rolled in off the hills. 583 people died, which still makes it the deadliest accident in aviation history. The KLM jet started its takeoff roll while the Pan Am jet was still taxiing towards it through the murk, looking for […]