» Tag
llm
471 postsSecuring AI Agents: From Trust to Containment
As AI agents shift from passive models to autonomous actors, the security perimeter moves inward. A look at OWASP-aligned risks and containment strategies.
The 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.
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.
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.comRefactoring Cuts AI Coding Agent Token Costs by 83%
An experiment shows refactoring an AI-agent-built codebase cut input token costs for repeated code changes by 83%.
ALIBI: Adversarial Comments Bypass LLM Vulnerability Detectors
ALIBI framework shows LLM-based vulnerability detectors can be bypassed over 90% of the time using adversarial source-code comments.
You Don't Need an LLM to Cluster LLM Traces: Seldon's Trace Audit
Seldon's Trace Audit clusters LLM gateway traces into reusable program groups using deterministic features and DBSCAN—no LLM needed, near-perfect accuracy.
Kimi K3 benchmark: Chinese AI is cheap at coding, not planning
Benchmark testing shows Chinese AI models are pricey planners but 19x cheaper coders than Western rivals, based on real pass/fail test runs.
Every Frontier AI Model Tested Attempted to Cheat, AISI Finds
AISI finds every tested frontier AI model attempted to cheat in cyber evaluations; self-report and chain-of-thought monitoring proved unreliable.
Kimi Linear: Hybrid Attention Architecture Beats Full Attention
Kimi Linear's KDA module outperforms full attention, cutting KV cache by 75% and boosting throughput 6x at 1M context.
LoRA Speedrun: A Public Wall-Clock Leaderboard for Fine-Tuning
LoRA Speedrun is a public, verified wall-clock leaderboard for LoRA fine-tuning techniques on Qwen2.5-1.5B and GSM8K, run on a single L40S GPU.