Tagged: coding-agents

22 articles

Latest

Funes Gives Claude, Codex, and Other Coding Agents a Searchable Memory That Stays Local

Qwen's zg search layer cut coding agent tool calls 43% in early tests

NVIDIA's Switchyard proxy lets Claude Code talk to any OpenAI model

DeepMind's new chief: 'Nothing other than being at the frontier' matters

Sandbox Cold Starts Are a Lie: Concurrency Tests Expose 2.7s Tails

AI Coding Agents Executed Malicious Code From 100+ Poisoned Docs

Mystery model Ox Alpha is actually Z.ai's GLM, weights drop Wednesday

The Harness, Not the Model, Is What Makes Coding Agents Good

Zhipu's GLM-5.3 found 2,436 bugs in code up to 40 years old

Google slashes Gemini 3.7 Flash pricing by 50% to $0.75 per 1M tokens

Shepherd can checkpoint a live agent process, not just files, and rewind it 5× faster than Docker

Prime Agent hits 95.5% on ARC-AGI-3, beating the human expert baseline

Meta ships Muse Code agent that survives crashes and runs 1,000+ tool calls over 24 hours

Supabase open-sources an AI agent benchmark — and 78% of coding agents flub auth without a skill file

OpenAI’s agents cut scientific code runtimes 60x, but the real bottleneck is verification

GPT-5.6's Sol model slashes coding costs by 50% while beating Anthropic's Claude

Hands-On: Kimi CLI Becomes a Non-Interactive Coding Agent That Ships Real Code

AI coding agents are rewriting genomics software, but the last 10% still takes human grit

Cursor's agent swarm rebuilt SQLite in Rust with 100% test pass rate, proving cheap models can ship

OpenAI's Codex moves from autocomplete to agent

GLM-5.2 crushes open-source coding leaders, lands within 4 points of Claude Opus 4.8

I turned a coding agent loose on 2 Hugging Face URLs and it built a 3D Paris