» Tag
verification
36 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.
New Verification Gate Catches AI Models' Silent Omissions
A layered verification gate now catches AI models that silently skip claims they should surface, splitting omission into checkable failure states.
Why Raft Rebuilt Notifications to Work for AI Agents, Not Just Humans
Raft's engineering team redesigned notification architecture after discovering AI agents can't selectively ignore messages the way humans do.
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.comProof-Carrying-BPF Programs Aim to Expand eBPF Verifier Acceptance
A SOSP '26 paper proposes proof-carrying-BPF programs, letting the eBPF verifier accept complex programs it previously rejected via formal proofs.
AI Circuit Tutor That Can't Draw a Wrong Circuit
How digiwleea's AI circuit tutor uses netlist verification and simulation feedback to guarantee every generated circuit is provably correct.
The Real Divide in AI Verification: Code vs. Judgment
An AI agent's false 'I will remember' claim exposed why code-based gates, not judgment calls, are needed to verify agentic AI workflows.
AI Agents for Mathematicians: Beyond Chat-Based Prompting
Why agentic harnesses like Codex outperform chat prompting for tackling open math conjectures, with durable state and strict verification labels.
Designing a Coding Agent Loop: Goals, Verification, Stopping
How to design a coding agent loop: goal-check separation, a verification ladder, isolated attempts, and explicit stopping states.
Cross-vendor byte-identical inference for a 72B LLM (AMD MI300X vs. Nvidia H100)
A new protocol enables byte-identical outputs from a 72B LLM using AMD MI300X and Nvidia H100.
Making LLM Extraction Trustworthy Enough to Act On
Honeycomb addresses the verification processes needed to enhance LLM extraction trustworthiness.