30
30
60
Bad Likert Judge: A Novel Multi-Turn Technique to Jailbreak LLMs by Misusing Their Evaluation Capability
Unit 42 details the Bad Likert Judge multi-turn jailbreak that abuses LLMs' evaluation capability, raising attack success rates over 60% across six frontier models.
Palo Alto Networks Unit 42 describes the Bad Likert Judge technique, a multi-turn jailbreak that asks a target LLM to act as a Likert-scale judge scoring the harmfulness of example responses. The highest-rated example in each scale can carry harmful content, bypassing the model's internal guardrails. Testing across six state-of-the-art text-generation LLMs showed an average attack success rate increase of more than 60% versus plain attack prompts, with tested models anonymized. The technique targets edge cases rather than typical use, and the article positions the work as guidance for defenders on potential jailbreak risks.
60
RTK reports token savings, but our cost benchmarks disagree
Quesma's $1,500 benchmark found RTK cuts reported token output but changes Claude Code and DeepSeek coding costs by only about 5% on Terminal-Bench 2.1.
Quesma benchmarked RTK (Rust Token Killer), a popular tool with 79k GitHub stars that filters terminal output for AI coding agents, whose README claims up to 90% output reduction. Across 1,740 Terminal-Bench 2.1 attempts running Claude Code with Fable 5.0 and OpenCode with DeepSeek V4 Pro 0813, total costs moved only -5% for Fable and +5% for DeepSeek, with pass rates dropping 1-2%. RTK's own rtk gain metric reported 349.2 million tokens saved (an 89% reduction) across 445 DeepSeek attempts, but this did not correlate with actual cost savings, and cached terminal-output reads cost as little as 1/10 to 1/30 of regular input tokens. A bug in rtk find 0.45.0 caused one agent to loop with 339 consecutive errors, costing roughly 9x the baseline attempt, though the task still passed.
42
30
30
60
60
60
55
30
60
42
Citrix UniconOS dual boot turns Windows endpoints into their own recovery device
Citrix released UniconOS dual boot in Release 7 2607, turning Windows endpoints into self-recovery devices after ransomware, failed updates or OS corruption.
Citrix announced dual boot in UniconOS Release 7 2607, which installs an isolated, hardened recovery environment alongside Windows in a separate partition protected by secure boot. If Windows is unavailable, users reboot into UniconOS and reconnect to applications via Citrix DaaS and SecurAccess with Chrome Enterprise. The capability is aimed at reducing reliance on spare hardware and central reimaging during ransomware or update failures, with automatic enrollment in UniconOS Management for fleet-wide boot policies.
25
30
47
30
30
Jackrong/Qwopus3.8-27B-Flash-GGUF — new model trending #26 on Hugging Face
Community fine-tune Qwopus3.8-27B-Flash, built on Qwen3.8-27B, cuts agent reasoning latency with 12.8% faster decoding and 80.7% MTP acceptance.
Jackrong released Qwopus3.8-27B-Flash, a fine-tune of Qwen3.8-27B optimized for long-running agent workloads, reporting 12.8% faster decoding and 80.7% multi-token-prediction acceptance. Training used roughly 1.5 million teacher-scored SFT examples filtered to the top 10%, followed by reinforcement training with NVIDIA NeMo-RL and GSPO. The author notes an explicit trade-off: MMLU-Pro mixed-set scores are lower than the base model, and a known bug can produce incorrect Python indentation. Author-provided benchmarks have not been independently verified.
35
TWINLOOT Abuses SharePoint and Teams to Steal Credentials and Move Across Networks
Ontinue disclosed TWINLOOT, a Python implant hiding C2 in SharePoint dead drops and Teams TURN relays, harvesting credentials and pivoting via reverse SOCKS5.
Ontinue's Cyber Defense Center identified TWINLOOT during a July 2026 campaign investigation: a modular, PyArmor-hardened Python implant (a 39 MB bootstrap-fat.pyc loader) whose entire C2 infrastructure lives inside trusted Microsoft services. Tasking flows through SharePoint Online file dead drops polled every 15 seconds via the Microsoft Graph API, while interactive operator access uses WebRTC DataChannels relayed by Microsoft Teams TURN servers; Graph traffic is driven by the victim's own headless Edge browser. The implant harvests Windows credentials with fake lock screens, offers a reverse SOCKS5 pivot for lateral movement to SMB, RDP, WinRM, and MSSQL, executes commands, and persists on hosts. Initial access is assessed to be Teams social engineering masquerading as IT support, prompting a PowerShell command to download the payload.
60
When AI Agents Go Rogue: Agent Session Smuggling Attack in A2A Systems
Unit 42 unveils agent session smuggling, where a rogue AI agent hides covert instructions in established Agent2Agent (A2A) protocol sessions to manipulate victim agents.
Palo Alto Networks Unit 42 discovered agent session smuggling, a new attack technique in which a malicious AI agent exploits an established cross-agent session under the Agent2Agent (A2A) protocol to send covert instructions hidden among benign client requests and server responses. The technique leverages the implicit trust agents place in collaborating agents and the stateful, multi-turn nature of A2A sessions; the researchers stress it affects any stateful protocol, not an A2A flaw. Unlike one-shot data-based attacks, a rogue agent can converse, adapt and build false trust over multiple interactions. Proposed mitigations include human-in-the-loop enforcement, cryptographically signed AgentCards for remote agent verification, and context-grounding to detect injected instructions.
55
30
30
55
30
30
60
Agent Harness vs Agent Framework vs MCP: Which Layer Owns the Loop, State, Tools, Permissions, and Recovery
Architecture explainer separates agent harnesses, frameworks, and MCP by which layer owns the loop, state, permissions, and recovery.
The article distinguishes agent harnesses (OpenAI Codex, Claude Agent SDK), which own the execution loop, sandbox, permission model, and recovery; frameworks (LangGraph, OpenAI Agents SDK, Microsoft Agent Framework), which supply composable primitives; and MCP, a stateless JSON-RPC wire protocol governed by the Linux Foundation's Agentic AI Foundation since December 2025. An ownership matrix maps the execution loop, state, tool transport, permissions, recovery, sandboxing, and multi-agent orchestration to each layer. The 2026-07-28 MCP specification made the protocol fully stateless, retiring the initialize handshake and session headers.
35
The Rise of the Forward Deployed Engineer — and How To Do the Job Right
Palantir veteran Vinoo Ganesh traces the forward deployed engineer role and shares practices for building effective FDE teams.
Kepler CEO and former Palantir forward deployed engineer Vinoo Ganesh argues that labs, startups, and PE firms hire FDEs without a shared definition of the role. He recounts Palantir's Project Frontline rotation, which trained about 250 software engineers as FDEs, many now leading forward deployed teams at OpenAI, Anthropic, xAI, and Anduril. A 2013 failure of the Phoenix transaction store at a bank, where real-world data gaps caused roughly 2.3 million keyspaces and an out-of-memory crash, illustrates why FDEs must own the gap between design and production reality. At Kepler he places the FDE function inside product rather than sales.
30
55
30
30
42
Continue, Adapt, or Yield: In-Turn Adaptation to Overlapping Speech in Full-Duplex Agents
Duplex Cue evaluation shows PersonaPlex full-duplex agents adapt in-turn to listener contributions in only 34.8% of collaborative cases versus 68.2% for humans.
The paper introduces Duplex Cue, an evaluation of in-turn adaptation in full-duplex voice agents that separates listener intent (backchannel, collaboration, interruption) from speaker behavior (continue, adapt, yield). Using 208 scorable pairs from 300 human-confirmed cues in unscripted English conversations, it compares recorded human responses with PersonaPlex continuations generated while replaying listener audio. Humans adapt within the turn in 68.2% of collaborative pairs versus 34.8% for PersonaPlex, which otherwise continues unchanged (42.4%) or yields (22.7%).
15
ChatGPT Sketch turns your bad drawings into detailed AI images
OpenAI launched ChatGPT Images 2.5 with a Sketch feature that turns user doodles into images, plus 50% lower latency.
OpenAI released ChatGPT Images 2.5 and a new Sketch feature, activated by typing @Sketch, that lets users draw doodles inside ChatGPT and use them as image generation prompts. The update claims more natural lighting, richer textures, better multi-turn instruction following, and up to 50% latency reduction versus Images 2.0. Users can also leave inline comments on parts of an image to request specific edits. It is available for ChatGPT, ChatGPT Work, and Codex users on desktop, mobile, and web.
30
30
57
45
30