» curated · synthesized
Skip the noise.
Read the signal.
Curated tech news and synthesis for developers and technology professionals.
» Latest posts
379 posts28.9M Parameter LLM Runs Fully On-Device on an $8 Microcontroller
An 28.9M parameter LLM runs entirely offline on an $8 ESP32-S3 chip using Google's Per-Layer Embeddings technique for flash-based storage.
@ttsc/graph: A Compiler-Built Code Graph MCP for AI Agents
@ttsc/graph is an MCP server using the TypeScript compiler's own type-check to build a code graph, cutting AI agent token use by about 90%.
How We Self-Host DeepSeek V4 Flash on AWS Spot Instances
Inside a self-hosted DeepSeek V4 Flash deployment on AWS spot GPUs: MXFP4 quantization, RTX PRO 6000 hardware, DSpark decoding, and KV cache tuning.
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.comNew Linux benchmark tests corruption, snapshots, rebuilds on 26 layouts
Open-source Linux benchmark tests btrfs, ZFS, bcachefs, ext4 and XFS across 26 configs for corruption, snapshots, rebuilds and ENOSPC handling.
Agent-Native Software Engineering: Why Specs Alone Aren't Enough
Coding agents fail less at writing code than at holding architectural context. A look at spec-driven development's limits and what comes next.
JavaScript's Date Object: The Hidden Traps Breaking Production Code
A technical breakdown of JavaScript's Date parsing, mutation, and timezone traps, and how the new Temporal API fixes them for engineers.
Are AI Labs Gaming the Pelican-on-a-Bicycle Benchmark?
A statistical study generates 1,008 SVGs across 7 LLMs to test whether AI labs are secretly optimizing for the famous pelican-on-a-bicycle benchmark.
Emem: A Signed Memory Layer for Multi-Agent AI Systems
Emem gives AI agents a signed, verifiable memory layer for physical-world facts that survives context compaction across models and vendors.
Slater: A Low-Memory GraphDB for Graphs That Don't Fit in RAM
Slater brings disk-native, low-memory graph storage with full neo4j Bolt compatibility, live writes, and built-in vector search.
Lucen parallelizes Python loops via two comments, bit-identical results
Lucen parallelizes Python for loops via two comments, guaranteeing bit-identical results versus sequential execution. Rust-accelerated, v1.1, Apache-2.0.