» Tag
llm
473 postsAI Agents in Production: Why 88% of Enterprise Pilots Fail
Why 88% of enterprise AI agent pilots stall before production, and the isolation, identity, secrets, and audit controls the successful 12% use.
Over 30% of new arXiv papers now read as AI-written
A 12,750-paper arXiv study finds ~32% of new submissions score as AI-written, using a false-positive-calibrated detector and detailed field breakdowns.
How Compiling an AI Agent's Workflow Cut Token Use by 94%
An engineer compiled a recurring AI agent workflow into deterministic code, cutting token use 94% and latency 87% with no quality loss.
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.comKernel devs review two LLM-assisted memory management patch sets
Two LLM-assisted Linux kernel patch sets—1GB huge page allocation and VM memory tracking—reveal how maintainers judge AI-assisted code.
Token Drift Explained: Why AI Agents Get Slower and Pricier
A breakdown of token drift in LLM agents: why session costs grow quadratically and how context budgets keep long-running agents efficient.
Favur Evals: a public benchmark for which AI model codes best
Favur Evals is a public, vendor-independent leaderboard comparing AI models on real software engineering tasks across eight measurable dimensions.
Engineering notes: making an AI system tell the truth
How NicheIQ rebuilt its AI idea-evaluation pipeline to fix self-scoring bias, failed self-refinement loops, and reach an honest No-Go verdict.
Fine-Tuned LFM2.5 Powers a Tool-Calling Agent Entirely in the Browser
A fine-tuned LiquidAI LFM2.5 model runs a tool-calling agent fully client-side in the browser - no server, no API key, zero cloud cost.
Building an AI Website Generator for Nigerian SMBs: Architecture & Lessons
How WebDigitize generates multi-page sites for Nigerian SMBs using Next.js, FastAPI, and Claude — plus key lessons on Puck JSON schema design.
Researcher Tricks Claude Into Leaking User Secrets via Web Fetch
How a researcher exploited Claude's memory and web_fetch tool to silently exfiltrate a user's name, employer, and security answers letter by letter.