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...
EvoCode-Bench tests coding agents across 227 sequential rounds in a persistent workspace. Single-turn scores overstate reliability — regressions, not missing features, are the real bottleneck. Context & related coverage →
In the following case study, the AI coding agent rebuilds a core system invariant in just three days, with minimal human input, running 31 verification passes and correcting 201 errors, before shipping code with zero... Context & related coverage →
New Inkling model family with a full support stack: base modeling , piecewise CUDA graph support , Hopper FA4 relative attention , MTP=1 speculative decoding... · DeepSeek-V4 performance push across vendors: a special... Context & related coverage →
SmithDB supports full-text search and JSON filtering over agent traces with a median (P50) latency of 400 ms, even though the underlying data consists of large, deeply nested JSON documents stored in object storage. Context & related coverage →
Traditional API gateways assume deterministic services and simple schemas - assumptions agentic AI breaks. Discover why enterprise engineering leaders are adopting AI Gateways as an evolutionary architecture seam. Cen... Context & related coverage →
Ruff v0.16.0 Astral shipped a significant new version of their Ruff Python linting tool a few days ago on July 23rd. I noticed today because my various CI jobs all started failing thanks to new default Ruff checks and... Context & related coverage →
China blows past America on AI. Congress may stop us from catching up Washington Examiner Context & related coverage →
Release 0.146.0-alpha.12 Context & related coverage →
An Inside Look at the Relay Market Powering Token Resellers and Fraud Fascinating investigation by Matt Lenhard into the market that has grown up around reselling LLM tokens at a discount by pooling API keys from vari... Context & related coverage →
LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fundamental dilemma between task diversity and verification reliabili... Context & related coverage →
Adding procedural skills to an LLM agent is typically evaluated by average improvement in task success. However, this metric hides an important cost: skills can also make agents worse. We measure both sides by compari... Context & related coverage →