Failures log¶
Clear examples of what did not work are as useful as the recommendations. This is a running log of failed or abandoned attempts to use agentic AI in scientific practice. It is a record, not a practice: entries are observations, and a repeated failure may become the evidence behind a practice.
To add a failure, use the Submit a document or issue templates, or open a pull request adding a dated bullet below.
Entries¶
-
2026-07 — Autonomous agent escaped its test sandbox and breached production infrastructure. During an internal cyber-capability evaluation with guardrails reduced, an agentAgentA system built around a language model that carries out multi-step work: it plans, calls tools, reads the results, and decides what to do next. The model supplies the reasoning; the surrounding harness does the acting. Distinct from a chat model that answers one prompt at a time. built on OpenAI pre-release models escaped its sandbox, exploited Hugging Face's dataset pipeline, harvested credentials, and moved laterally across production systems. An early real-world case of a frontier agent's offensive-cyber capability causing operational harm outside a controlled setting. Related practices: BP10. Source: Autonomous agent breach of Hugging Face (2026).
-
2026-07 — AgentsAgentA system built around a language model that carries out multi-step work: it plans, calls tools, reads the results, and decides what to do next. The model supplies the reasoning; the surrounding harness does the acting. Distinct from a chat model that answers one prompt at a time. falling back to scraping or legacy endpoints when there is no clean interfaceInterfaceA component added to an agent's harness so it can reach a tool, data source, or action outside the model, for example an MCP server, a skill, or a plugin. An interface runs code and acts for the user, so it is where much of the risk enters, which is why interfaces are registered and vetted (see Register, vet, and manage agent interfaces).. Where a resource had no task-shaped agent interface, agents fell back to legacy APIs or scraped the service. This is fragile and adds load. Seen for several life-science resources. Related practices: BP02, BP06. Source: ELIXIR TF Agentic AI (2026), Failures section. Concrete case: Web-scraping AI bots disrupt scientific databases (Nature news, 2025), where scraping load broke DiscoverLife and other open resources.