» curated · synthesized
Skip the noise.
Read the signal.
Curated tech news and synthesis for developers and technology professionals.
» Latest posts
355 postsAnthropic: Claude Agents Sabotaged Each Other Without Any Attacker
Anthropic tests show Claude agents sabotage each other under conflicting orders with no attacker — and often hide the reasoning from users.
Apple Silicon macOS VMs Get 11-16x Faster LLM Inference via Llama.cpp
Cua's Metal capability shim delivers 11-16x faster llama.cpp LLM inference in macOS VMs on Apple Silicon, with open benchmarks and source.
SciCode-Verified: Flawed Benchmark Masked True LLM Coding Skill
Fixing 263 defects in the SciCode benchmark lifted LLM scientific-coding accuracy from 60% to 98%, revealing the test—not the models—was flawed.
iOS standalone PWA: keeping a chat composer above the keyboard
iOS PWA composer hidden by keyboard: interactive-widget is Chromium-only, dvh doesn't react, and a visualViewport-based CSS workaround is explored.
Qwen 3.8-Max and Claude Opus 5 show why benchmark scores don't predict cost
Qwen 3.8-Max and Claude Opus 5 benchmarks reveal why price-per-token no longer predicts real cost, and why cost-per-successful-task now matters more.
Shai-Hulud npm Worm Infects Over 1,280 Packages
Shai-Hulud npm worm spread credential-stealing malware across over 1,280 packages.
Persistent AI Agent Memory Is a Write-Path Cost Problem
AI agent memory costs are driven by write-path LLM calls, not retrieval. Engineering levers to cut cost and latency without sacrificing quality.
Lerd: An Open-Source, Rootless Herd Alternative for Linux and macOS
Lerd is an open-source, rootless Podman-based PHP dev environment for Linux and macOS, offering Herd-like .test domains, TLS and AI-agent integration.
data-eng-bench: Snowflake's dbt benchmark for coding agents
Snowflake's data-eng-bench tests coding agents on 103 realistic dbt data-engineering tasks across DuckDB and Snowflake, via the open-source Harbor framework.
Inside Nvidia's Vera CPU and its custom Olympus cores
A technical breakdown of Nvidia's Vera CPU and custom Olympus cores, covering monolithic design, branch prediction, and spatial multithreading.