Greg Kroah-Hartman's Clanker T1000: Local LLM on Framework Desktop with AMD Ryzen AI Max Fuzzing Linux Kernel Bugs
Greg Kroah-Hartman, the stable maintainer of the Linux kernel, has revealed the hardware behind his gregkh_clanker_t1000 — an AI-based fuzzing tool that has been uncovering kernel bugs. Running a local large language model (LLM) on a Framework Desktop powered by an AMD Ryzen AI Max+ "Strix Halo" processor, Greg has already contributed nearly two dozen patches merged into mainline Linux since April 7.
Key Details
- Hardware: Framework Desktop with AMD Ryzen AI Max+ (Strix Halo) — a CPU/APU known for strong iGPU and LLM performance on open-source software.
- Bugs Fixed: Patches address issues in ALSA, HID, SMB, Nouveau, IO_uring, and other kernel subsystems.
- Approach: Local LLM (not cloud-based) used for fuzzing and bug discovery. Greg shared a photo of the rig on Mastodon, but has not yet disclosed the software stack details.
- Impact: Demonstrates a practical alternative to relying on cloud LLMs for kernel security testing, with dozens of bugs already fixed.
Who It's For
Linux kernel developers interested in AI-assisted fuzzing or choosing local hardware capable of running large models for development tasks.
📖 Read the full source: HN AI Agents
👀 See Also
AI's Affordability Crisis: OpenAI and Anthropic Burn $8–$14 to Make $1
DSHR's analysis reveals AI platforms subsidize tokens by 40-70x; OpenAI lost $38.5B in 2025 on $13B revenue, spending 44% on sales & marketing.
Six Research-Backed Parallels Between LLM Failure Modes and ADHD Cognition
A developer with ADHD identifies six parallels between LLM failure patterns and ADHD cognitive science, backed by independent research on associative processing, confabulation, working memory limitations, pattern completion, structure dependence, and thread continuity.
Anthropic Urges Global Pause in AI Development, Flags Self-Improvement Risk
Anthropic has called for a global halt on training frontier AI models, citing risks from self-improving systems. The WSJ article details the proposal's scope and rationale.
Cursor's Composer 2.0 appears to use Kimi 2.5 model based on API endpoint evidence
Network analysis shows Cursor's Composer 2.0 sends requests to an endpoint containing 'kimi-k2p5-rl-0317-s515-fast', suggesting it's based on Kimi 2.5. The modified MIT license reportedly requires attribution but minimal other obligations.