» curated · synthesized
Skip the noise.
Read the signal.
Curated tech news and synthesis for developers and technology professionals.
» Latest posts
1032 postsMechanistic View Reveals How Bias Lives Inside LLM Judges
Study shows LLM-as-judge bias is encoded in activation geometry, enabling causal steering and better failure prediction than text-based methods.
"Hallucination" Isn't One Bug. It's Three, and Only One Is Fixable
Hallucination isn't one failure mode — it's three. A test to tell them apart, why benchmarks reward bluffing, and what a 2026 prediction experiment showed.
Why $/Token Pricing Hides the Real Cost of Frontier AI Models
Frontier AI pricing pages hide tokenizer differences that can inflate real costs by up to 73% on code like TypeScript, per new billing analysis.
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.comIETF Draft Lets IPv4 Run ARP-Free as a Service on IPv6-Only Nets
New IETF draft removes ARP and IPv4 subnets from IPv6-only networks, turning IPv4 into a pure host service via a sentinel gateway address.
AEGIS: An Open-Source, Self-Hosted Personal AI Orchestration System
Developer open-sources AEGIS, an MIT-licensed, self-hosted personal AI orchestration platform built on FastAPI, Postgres, and Temporal.
VetoBench Tests Whether AI Agent Memory Retains Rejected Decisions
VetoBench is an open benchmark testing whether AI agent memory systems retain and surface previously rejected technical decisions.
Claude Code Burns 33K Tokens Before It Even Reads Your Prompt
Wire-level analysis shows Claude Code sends 33K tokens before reading your prompt - 4.7x OpenCode, with 3.7x higher real-task costs.
Hermes Agent: A Self-Improving AI Framework With Persistent Memory
Nous Research's open-source Hermes Agent framework combines persistent memory, reusable skills, and a real multi-agent architecture for self-improving AI.
Benchmarking a Markdown Knowledge Graph as AI Agent Memory
IWE tested markdown knowledge graphs as AI agent memory using the LOCOMO benchmark, reaching 96% of a hand-built ceiling with a cheap curator model.
Popular ModHeader Chrome Extension Exfiltrates User Data
Reverse engineering reveals ModHeader, a 1.6M-install Chrome extension, secretly exfiltrates encrypted browsing data via a hidden AES-GCM pipeline.