» Tag
llm
471 postsAI 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.
LLMs 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.
Building Reliable Software With Untrustworthy AI Agents
A practical framework for reliable AI-agent coding: context window management, verification layers, CLAUDE.md briefs, and reusable skills.
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.comTurboFieldfare runs Gemma 4 26B MoE model in 2GB RAM on any Mac
TurboFieldfare is an open-source Swift/Metal runtime that streams MoE experts to run Gemma 4 26B in just 2GB RAM on 8GB Apple Silicon Macs.
ButterClaw: Self-Hosted Runtime Security for AI Agents, No Cloud
ButterClaw enforces AI agent security locally with regex signatures, a local LLM verdict pipeline, and SIGKILL/credential shredding — no cloud, no telemetry.
CodeCrucible: A Reusable Blueprint for LLM-Driven SAST
Block's CodeCrucible offers a reusable design blueprint for LLM-driven SAST, using whole-repo analysis instead of snippet-anchored vulnerability scanning.
Running Kimi K3, a 2.8T-Parameter MoE Model, on an M1 Mac
Deltafin runs Kimi K3, a 2.8T-parameter MoE model, on a 64GB M1 Mac via full local install or expert streaming, no cluster required.
Ctxdiff Brings Git-Style Diffing to LLM Agent Context Windows
Ctxdiff is a local-first, open-source tool that applies git-style diffing to LLM agent context windows, turn by turn.
Static Scanner Finds 30 Unguarded Destructive Actions in AI Agent Frameworks
An open-source scanner analyzed 25 AI agent frameworks and confirmed 30 cases where models can delete data, deploy, or send webhooks unauthorized.
Toolgz cuts LLM tool-definition tokens by ~80% without accuracy loss
Toolgz reduces LLM tool-definition token usage by ~80% while preserving accuracy, validated across 420 runs on four frontier models.