» curated · synthesized
Skip the noise.
Read the signal.
Curated tech news and synthesis for developers and technology professionals.
» Latest posts
2695 postsThinking Machines Lab Ships Inkling: 975B-Param Open MoE, Tunable Reasoning
Thinking Machines Lab's 975B-param, 41B-active Inkling model offers encoder-free multimodality and a tunable reasoning-effort control.
A Green Test Suite Isn't Proof: Authority Gaps Slipped Past 16/16
A 16/16 passing test suite hid three critical gaps in an authority model. Why a green scoreboard alone was never sufficient proof.
AI Migrates COBOL to Java Fast — Proving It's Correct Is Hard
AI speeds up COBOL-to-Java migration, but proving correctness is the hard part. How an SMT-based equivalence verifier catches hidden bugs before they ship.
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.comWe gated CI on six LLM eval frameworks — only two survived
An eight-month CI test of six LLM eval frameworks found only Promptfoo and DeepEval reliable as merge-queue gates, thanks to deterministic checks.
MCP's Confused Deputy Problem: Provenance Gaps, Injection, DNS Rebinding
MCP's confused deputy flaw explained: provenance gaps, prompt injection via fetch servers, DNS rebinding, and concrete detection rules.
MIT Method Detects AI Models Fine-Tuned for CSAM Without Generating It
MIT and Thorn's Gaussian probing technique flags AI models fine-tuned for CSAM generation with 100% accuracy, without producing any illegal images.
A Practical Pre-Deploy Security Checklist for Solana Anchor Programs
A systematic pre-mainnet security checklist for Solana Anchor programs, covering account validation, arithmetic safety, CPI checks, and Wormhole exploit lessons.
Claude Code Skills Guide: Automating Your Dev Workflow
How Claude Code's Skills evolved into a directory-based standard, with frontmatter controls and a real /code-review workflow example.
How do you actually test if an AI understands your codebase
A hands-on benchmark for testing whether an AI agent truly understands codebase structure, tested across thirteen real Ruby projects.
Colibri lets 744B-parameter GLM-5.2 run on just 25GB of RAM
Colibri is a single-file C engine that runs GLM-5.2's 744B MoE model on 25GB RAM with no GPU, streaming experts from NVMe on demand.