news
Gas City is an SDK and successor to Gas Town by Steve Yegge, announced April 24, 2026. Where Gas Town shipped a single, opinionated multi-agent platform, Gas City deconstructs the architecture into composable building blocks called "packs" so developers can assemble teams of collaborating AI agents
news
Experimental AI assistant launched in April 2026 on top of Sci-Hub. It answers research questions using full-text articles from the Sci-Hub corpus instead of summaries or abstracts; the corpus serves as a retrieval ground that constrains generation to actual passages from real papers.
news
A W3C proposal enabling web developers to access browser-provided or OS-provided language models directly via a JavaScript API. Supports prompt-completion workflows with stateful sessions, streaming, structured outputs, and multimodal inputs — all running on-device with no cloud dependency.
news
Just published a new piece — Heavy AI Agents Are an Anti-Pattern: Why Fewer Agents With More Skills Wins.
news
Tolaria is a free, open-source desktop app for managing markdown knowledge bases, created by Luca Rossi (author of the Refactoring newsletter). Positioned as "a second brain for the AI era", it stores everything as plain Markdown files with YAML) frontmatter on disk, ships a block-based editor with
news
Qwen3.6-27B is a dense, natively multimodal 27B-parameter open-weight LLM) from the Qwen family (Alibaba Cloud), released on 2026-04-22. It targets the "flagship-quality model that fits on a single high-end consumer GPU" slot in the lineup, sitting alongside the smaller MoE Qwen3.6-35B-A3B and the A
news
OpenAI Privacy Filter is an open-weight, Apache 2.0-licensed token-classification model published by OpenAI on HuggingFace for detecting and masking personally identifiable information (PII) in text. It is designed for high-throughput data sanitization workflows: feeding LLMs, redacting datasets, on
news
Fourth-generation flagship release from Deepseek (April 24, 2026). Two open-weight variants — V4-Pro (1.6T total / 49B active parameters) and V4-Flash (284B total / 13B active) — both built on a MoE) architecture, ship with a 1M-token Context Window by default, and fold what was the separate R reaso
news
DESIGN.md is an open Apache-2.0 format specification from Google Labs for describing a design system to coding agents in a single, version-controllable file. It pairs machine-readable design tokens in YAML front matter with human-readable design rationale in markdown prose — so an LLM) can apply vis
news
A plugin that turns a structured Obsidian note tree into an actual book; exported to EPUB and PDF.
news
A family of attention mechanisms that compute interactions between only a subset of token pairs instead of every pair, breaking the O(n²) cost of full self-attention. The dense attention used in vanilla Transformers forces every token to attend to every other token; sparse attention restricts that i
news
AI models whose trained weights are publicly released, allowing anyone to download, run, fine-tune, and deploy them. "Open weight" is more precise than "open source" because most releases don't include training code or data.
A clear roadmap to building your own knowledge system. Subscribe and get it straight to your inbox.
6,000+ readers. No spam. Unsubscribe anytime.
