AI news for platform & agent engineers
Ranked signal · finite reading
One shared ranking. Scan what changed, save what matters, and stop when the finish line appears.
Loading...
Mixture-of-Experts (MoE) models scale capacity without proportional compute cost and have become a key architecture for frontier large language models (LLMs). Yet domain-specific post-training inherits an expert pool... Context & related coverage →
Active flow control involves nonlinear dynamics, partial observations, and computationally expensive simulations, making controller design particularly challenging. Deep reinforcement learning (DRL) has emerged as a p... Context & related coverage →
Multi-scene navigation (clearing an objective in one bounded space and then crossing a portal into the next) is a defining feature of contemporary 3D games, but authoring it is laborious: every portal must have consis... Context & related coverage →
Added screen reader mode: opt-in plain-text rendering for screen reader users. Run claude --ax-screen-reader , set CLAUDE_AX_SCREEN_READER=1, or add "axScree... · Added vimInsertModeRemaps setting: map two-key insert-... Context & related coverage →
a quiet day lets us fact check some numbers against the sound of silence of Claude Code reporting... Context & related coverage →
TIL: Using uvx in GitHub Actions in a cache-friendly way I finally found a cache-friendly recipe for using uvx tool-name in GitHub Actions workflows that I like. The trick is setting a UV_EXCLUDE_NEWER: "2026-07-12" e... Context & related coverage →
We analyzed 300,000 real conversations to measure the values Claude expresses across models and languages, compressed into four interpretable axes. Context & related coverage →
DOOMQL Peter Gostev built this using GPT-5.6 Sol. This is a lot of fun: DOOMQL started with a deliberately unreasonable question: what if SQLite were the game engine, not merely the place where a game stores data? The... Context & related coverage →
Large language models are increasingly used to assist scientific reading, but existing evaluation methods often fail to detect whether answers are supported by verifiable citations. We introduce ResearchQA, a benchmar... Context & related coverage →
DoorDash details the architecture behind Ask DoorDash, its AI-powered conversational shopping assistant, combining LLMs, specialized AI agents, MCP-based tooling, and an intelligence layer with persistent consumer mem... Context & related coverage →
Escaped untrusted fields in Slack issue notification workflow : Fixed the Slack notification workflow to properly escape issue titles and usernames using jq... · Updated bundled Claude CLI to version 2.1.208 Context & related coverage →