OpenAI's safety team trained an attacker model to craft prompt injections that do two things at once: achieve a malicious goal, and induce the compromised agent to copy the injection into whatever it sends back out. In the clearest example,…
In the News: September 28, 2026 (Extra 2)
OpenAI discloses a prompt injection that replicates itself through an agent's own replies, and Anthropic ships Sonnet 5.5 at up to 30% lower cost per task.
Extra edition
Machine-readable
Download Markdown
Story
OpenAI discloses a self-replicating prompt injection that spreads through an agent's own replies
Read story →
Story
Claude Sonnet 5.5 cuts cost per task by up to 30% with a large jump on coding benchmarks
Sonnet 5.5 keeps Sonnet 5's list price, $2 per million input tokens and $10 per million output tokens, but Anthropic says it needs far fewer tokens to finish the same work, cutting cost per task by up to 30% and generating output more…
The Problem is not the AI Code, but Nobody Knows Anything Anymore
September 26, 2026. A widely shared account of an engineer whose team now produces specs, code, and tickets entirely through Claude Code, with Späti's own conclusion that the risk is not the generated code but a team that ships without anyone holding a plan.