» curated · synthesized
Skip the noise.
Read the signal.
Curated tech news and synthesis for developers and technology professionals.
» Latest posts
109 postsvoidguard: A Static Scanner That Catches Tests That Verify Nothing
voidguard is an open-source static scanner that flags tests, type checks, and CI conditions that pass while verifying nothing.
SDABench: A New Benchmark Testing LLMs on Scientific Discovery
SDABench evaluates LLMs on six scientific capabilities beyond code execution, exposing major gaps in assumption selection and mechanistic reasoning.
SynthDocBench Exposes Long-Context Weaknesses in Vision Language Models
New synthetic benchmark SynthDocBench reveals systematic VLM failures in long-context document understanding, including positional bias and chart errors.
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.comLSPS Specifications: How Lightning Service Providers Are Standardizing
A breakdown of LSPS0, LSPS1, and LSPS2 — the specs standardizing how Lightning wallets and service providers exchange channels and liquidity.
HyperShots renders App Store screenshots with CSS, not AI pixels
HyperShots generates App Store screenshots via CSS and headless Chrome at exact pixel specs, eliminating rejections caused by AI image models.
Building an Arch Linux Aarch64 Port for Holo Core
Collabora and Valve detail Holo Core, an unofficial aarch64 port of Arch Linux for Steam Frame, and the CI tooling needed to replay its build history.
Passwork's Hidden Russian Ties and FSTEC Certification Raise Concerns
OCCRP investigation reveals Passwork, an EU-marketed password manager, has undisclosed Russian founders and an FSTEC-certified Russian counterpart.
Kernel 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.
Moonshot AI Ships Kimi K3: A 2.8T-Parameter Open MoE Model
Moonshot AI's Kimi K3 is a 2.8T-parameter open MoE model with 1M context and new attention and routing architectures for long-context inference.