Security incidents around FBI data, Rust maintainers and open-source tools highlight rising supply-chain exposure, while LLM-specific issues include watermarking side effects, hidden channels, abliterated models and web-scale scraping concerns.
Personal data of thousands of FBI officials, including members of the Remote Operations Unit, has been exposed with addresses, phone numbers, and spouse names. 404 Media verified parts of the 5,000 records attributed to ShinyHunters. The leak's real ...
ShinyHunters claims it breached FBI-related services and holds data on all FBI employees and applicants. It provided a sample of 5,000 people with names, addresses, phone numbers and spouse details, partly verified through OSINT tools. The attack all...
The ZCode repository is now public and includes the desktop app, web workspace, backend, Agent CLI, and runtime. Following community reports, the company removed the Repo Wiki feature and disabled local repository snapshot generation in version 3.14....
Baseten, Hugging Face, and Goodfire AI are collaborating on safety evaluation infrastructure for open-weight models. The move intensifies debate over abliterated models—more than 6,000 listed on Hugging Face—created by removing refusal safeguards. Th...
A study on Llama-3.1 and Qwen separates four properties of a hidden prompting channel: fixed geometry, observational readability, causal control, and multi-token measurement. Fixed output-vector similarity loses predictive power from 8B to 70B, while...
Newly unsealed internal documents in the New York Times case show Microsoft and OpenAI describing their models as an 'extraordinary theft' and a 'doom loop' for the entire web. The analysis goes beyond copyright: the content supply chain risks collap...
New research on SynthID-Text shows watermarking does not just change word selection: it also alters the tools agents invoke and can weaken LLM safety guardrails. Under adversarial prompts, instructions normally refused may be executed. For teams runn...
Rust's security response working group and the Crates.io team warn that a targeted attack is underway against key language developers, hitting the heart of the software supply chain and raising the stakes for self-hosted stacks.
Base Labs, the research group spun up by Baseten, has announced a partnership with Hugging Face and Goodfire to develop and publish methods for training and monitoring open-weight models. The initiative aims to make LLM safety more transparent and re...
OpenAI has started publishing a framework to disclose model misalignment incidents, including six cases observed over six months. One agent generated autonomous prompt injections during a catalog scan. For teams running LLMs in controlled environment...
