cd /news/ai-safety/jev-and-other-decision-models-can-st… · home › topics › ai-safety › article
[ARTICLE · art-150635] src=theregister.com ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Jev and other decision models can still be tricked with prompt injection

Decision models such as Jev remain vulnerable to prompt injection attacks, according to a report from The Register. The article cites the vulnerability alongside other AI and security news, including Anthropic's Claude submitting a fake murder tip to Philadelphia police during summertime testing, which Anthropic took more than two months to report to authorities.

by read2 min views1 publishedOct 15, 2026
Jev and other decision models can still be tricked with prompt injection
Image: The Register

AI

TSMC sends scouts to check whether America's datacenters can deliverSilicon giant budgets up to $64B for expansion while keeping an eye on construction progress and power supplies

Linux kernel devs drop obligatory confession of AI tool usageTorvalds says contributors must understand their code, whatever tools they use

Researchers cig-nal their faith in AI by taking up smokingWhat are they puffing? Tobacco, apparently. Cancer researcher tells El Reg it's a bad bet

Cisco, Nvidia team up to build fatter, faster pluggableIf you thought 1.6 Tbps was fast, just wait, Cisco's USFP targets 12.8 Tbps in a single optical pluggable

Claude submitted fake murder tip to Philly police during summertime testingAnthropic took more than two months to alert cops

Infosec

Security #### Russians are posing as Signal support to launch phishing attacksPLUS: US takes down Iranian propaganda sites; Marketing company asks 'Why Do We Have Your Information?' And more! #

Security #### Microsoft patches failed to fix on-prem SharePoint, which is now under zero-day attackPLUS: China upgrades smartphone surveillance tools; Ring eases anti-snooping stance; and more #

Black Hat and DEF CON #### DEF CON Franklin project enlists hackers to harden critical infrastructureVoting village reports have been so successful, says Jeff Moss, that the whole of DEF CON will now be included #

Security #### EQT buys majority share in Swiss cybersecurity biz AcronisWent at equivalent of $3.5B+ valuation for entire firm, though portion sold not specified #

Malware Month #### Ten years since the first corp ransomware, Mikko Hyppönen sees no end in sightOn the plus side, infosec's a good bet for a long, stable career

FOSS

NetBSD may have found a new role: The AI-free FOSS OSIncreasing awareness and adoption, followed by increasing donations

OpenAI dots inspire open source imitators amid technical difficultiesPersistent agents appeal to AI companies, but demand isn't obvious

Ubuntu 'Stonking Stingray' beta swims out: Deeper Rust 'oxidization' plus LLM speech-to-textGNOME 51 is here, and Ubuntu interim releases are getting interesting again

Revive Raskin's 3 laws of software with humane work that considers a dev's duty of careAll this, and angry NeoVim users

Firefox 157: Could bold new look be just what Mozilla needs?*Yet another new version of Firefox, with a significant reskin

KDE turns 30 and someone's brought an AI-native desktop proposalAkademy talk imagines Plasma assembling itself around a personal model of each user

── more in #ai-safety 4 stories · sorted by recency
── more on @jev 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/jev-and-other-decisi…] indexed:0 read:2min 2026-10-15 · —