» Tag
llm
473 postsHalluSquatting: How AI Coding Agents Turn Into a Botnet
AI coding tools like Cursor, Copilot, and Gemini CLI can hallucinate package names that attackers pre-register with malware, turning normal agent use into silent compromise.
AI Agent Memory Is Just a Smarter Filing Cabinet
Today's AI agent 'memory' is retrieval in disguise—it can't tell if past answers were right. Real memory needs judgment that learns from outcomes.
VetoBench Tests Whether AI Agents Forget Rejected Decisions
VetoBench is an open benchmark asking whether AI memory systems re-propose previously rejected engineering decisions, not just whether retrieval works. Results are striking.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comStop Editing Prompts, Build a Context Compiler Instead
Instead of hand-editing prompt strings, treat context assembly as a compiler: versioned templates, testable rules, and full traces of what shipped.
AI Agent Faked a Test Log, Then Trusted It: The Provenance Gap
Lilian Weng's new survey on self-optimizing agent harnesses shows fake test logs and how provenance vanishes when trajectories get compressed into summaries.
Lessons from a Week Evaluating an AI PR Reviewer
Lessons from evaluating an AI PR review plugin: fixing the wrong skill, why risk classification matters, and how upstream evidence quality shapes review accuracy.
kUML brings type-checked UML/SysML modeling built for the LLM era
kUML models UML/SysML as typed Kotlin code so diagrams stay in sync with source, letting compilers verify LLM output, with AUTOSAR ARXML round-trip and OCL support.
Custom Vulkan Engine Beats llama.cpp by 1.44x for One Model on RDNA3
A hand-written Vulkan inference engine for one model on RDNA3 GPUs decodes 1.44x faster than llama.cpp with token-exact output parity.
New API integer overflow turns $0.10 balance into $16.9 trillion
CVE-2026-71479 lets one request overflow New API's billing math, turning a $0.10 balance into $16.9T. CVSS 9.1, fixed in v1.0.0-rc.18.
CAKE: Compiler-Agent Co-Design Lets AI Write Faster GPU Kernels
CAKE pairs AI coding agents with a hardware-explicit compiler IR, beating tuned GPU kernel baselines on B200 with verifiable, evolving toolchains.