» Tag
llm
48 postsNew Verifier Exposes Hidden Bugs in LLM-Generated GPU Kernels
A 12-gate contract verifier finds that 39.5% of LLM-generated GPU kernels are broken despite passing standard correctness benchmarks.
Study: LLMs Can Transmit Hidden Traits Through Unrelated Data
Research shows LLMs can transmit behavioral traits and even misalignment to student models via data with no semantic link to that trait, like numbers.
AI Jailbreak Benchmark Reveals 100x Safety Gap Between Models
New benchmark shows up to 100x safety gaps among frontier AI models against jailbreak attacks; some models yield zero jailbreaks.
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.comLLMs Are Honest in Prose but Hallucinate Under JSON Schemas
Study finds LLMs admit uncertainty in prose but fabricate data under required JSON schemas, with 10 of 13 models hallucinating 100% of the time.
Shoehorn: Rust Tool Quantizes LLMs to Fit Your Mac's Exact VRAM
Shoehorn is a Rust CLI that quantizes BF16 GGUF LLMs per-tensor to exactly fit your Mac's available VRAM, maximizing quality under a hard memory budget.
APC Framework Closes Authorization Gaps in Multi-Agent LLM Systems
A new authorization framework, APC, tracks delegated authority to block prompt-injection and unsafe action combinations in AI agents.
Unigram: A Rust Codec Turning Bytes Into Single-Token Words for LLMs
Unigram is a Rust crate encoding bytes into words that cost exactly one LLM token each, giving fixed token-budget guarantees over hex or base64.
GenRec: Netflix Moves Toward LLM-Native Recommendation Systems
Netflix's GenRec reframes recommendation as generative language modeling, signaling a shift from ranking pipelines to LLM-native architectures.
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.