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...
OpenWiki generates and maintains codebase documentation so coding agents can find the repo context they need without loading everything into one instruction file. Context & related coverage →
MiniMax-M3 : Added support for the new MiniMax-M3 model , with a fast follow-on of BF16/FP8 indexer via MSA , MXFP4 support , FP8 sparse GQA , and extensive... · DeepSeek-V4 keeps maturing : Following its debut, DeepS... Context & related coverage →
Release: llm-coding-agent 0.1a0 Another Fable 5 experiment. Now that my LLM library has evolved into more of an agent framework it's time to see what a simple coding agent would look like built on it. I started a new... Context & related coverage →
Elastic open-sourced Atlas, a system built on Elasticsearch that maintains three categories of memory for agents. Atlas integrates with agents via MCP and maintains per-user isolation of memories. When evaluated on qu... Context & related coverage →
Evaluating long-running, stateful agents needs a new kind of runner. Here's how Deep Agents, LangSmith sandboxes, and observability plug into Harbor. Context & related coverage →
Scaling inference compute, by generating many parallel attempts per problem, is a costly but reliable lever for improving language model capabilities. By default these attempts are generated independently, wasting inf... Context & related coverage →
shot-scraper video is a new command introduced in today's shot-scraper 1.10 release which accepts a storyboard.yml file defining a routine to run against a web application and uses Playwright to record a video of that... Context & related coverage →
Repository-level performance-optimization benchmarks such as GSO, SWE-Perf and SWE-fficiency evaluate coding agents by applying patches to real repositories and comparing runtime against unoptimized baselines and offi... Context & related coverage →
We introduce TiRex-2, a recurrent xLSTM-based time series foundation model that generalizes the univariate TiRex to multivariate forecasting with both past and future covariates. Real-world forecasting is inherently s... Context & related coverage →
Cassie Shum discusses the architectural evolution of GraphRAG and why data foundations are critical for advanced AI workflows. She explains how traditional vector RAG falls short when addressing global context, multi-... Context & related coverage →
Stacked slash-skill invocations like /skill-a /skill-b do XYZ now load all leading skills (up to 5), not just the first · Fixed SSL certificate errors (TLS-inspecting proxies, missing NODE_EXTRA_CA_CERTS , expired cer... Context & related coverage →