» Tag
llm
48 postsThe Hidden Risk of Giving LLM Agents Terminal Access
Giving autonomous AI agents shell access can wreck your filesystem. Open-source rewind-sdk uses OverlayFS to enable millisecond-fast checkpoints and rollbacks.
ai-agentsllmdevopslinuxClaude's Weights Are Closed, So a Live Thought Viewer for Qwen
Inspired by Anthropic's workspace paper, a developer built a live, token-level inner-thought viewer for the open Qwen model since Claude's weights are closed.
aiinterpretabilityllmanthropicWhy AI Agents Forget by Design: The Memory Problem
LLM APIs are stateless by design, and the context window is not real memory. This architectural choice drives cost, latency, and consistency failures in production agents.
ai-agentsllmmemorycontext-windowkUML 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.
kotlinumlsysmlllmBenchmarking Inference Energy Costs of LLM: A LLaMA Study
Researchers benchmark LLaMA model sizes on V100 and A100 GPUs to analyze the energy and compute costs of LLM inference at scale.
llmllamagpuenergy-efficiencyTreat the Context Window Like a Budget, Not a Junk Drawer
An open-source context-engineering framework has AI agents draft a context manifest before work begins, disciplining token budgets with decay rules and cross-platform parity checks.
ai-agentscontext-engineeringllmdeveloper-toolsVisionBridge: an MIT proxy that gives text-only LLMs vision capabilities
VisionBridge is a lightweight OpenAI-compatible proxy that lets any text-only LLM inspect images via a separate vision model, with no training or weights required.
llmvision-modelsopen-sourceproxyLLM Agent Performance Is a Distributed Systems Problem
FixBugs's team shows how token math, parallel chunking, and queues cut LLM agent latency: file analysis dropped from 10 minutes to 40 seconds.
ai-agentsllmdistributed-systemsperformanceJadepuffer: The First Fully Autonomous LLM Ransomware
Sysdig researchers documented Jadepuffer, the first fully autonomous LLM ransomware that exploited a Langflow flaw to breach database servers.
airansomwaresecuritylangflowA Deterministic Guard Stops LLM Agents From SQL Overfetching
An open-source, LLM-free guard checks agent-generated SQL against user roles before execution, preventing text-to-SQL systems from overfetching sensitive data.
llmtext-to-sqlaccess-controlai-agents