SevenTnewS

coding agents

9 published articles

Google DeepMindFeatured3 min read

Google's workhorse model, bigger in the 3.7 update

Gemini 3.7 Flash halves its price, then makes the case for it

Google's Gemini 3.7 Flash ships at half the intro price of 3.6 Flash while claiming gains on coding, web development, and knowledge-work benchmarks. The release lands three weeks after the previous Flash, and comes with a new price-performance argument for agent builders.

2026-08-16

AI4 min read

Multimodal / Open Source

Qwen plugin pack gives your coding agent eyes, hands, and video memory

Alibaba's Qwen team released Qwen-MM-Plugins, an Apache-2.0 toolkit that gives coding agents native multimodal skills: dynamic-resolution image and video reading, OCR, grounding, ASR, long-video memory, video generation, and thin-client control of Blender and FreeCAD. One script installs it across Claude Code, Codex, Qoder, OpenClaw, Qwen Code, and Gemini CLI.

2026-08-15

AI Agents7 min read

Terminal Security

The '$HOME' trap: AI coding agents need sandboxes, not 'allow?' prompts

Qoder's terminal sandbox blocks close to a hundred destructive agent commands every day. The cases behind those blocks explain why 'allow?' prompts fail: a project folder named $HOME, a cleanup that targeted /root, and a click that nearly cost an entire disk.

2026-08-13

AI IDEs4 min read

Alibaba / AI IDEs

Why Qoder 1.0 gave up on the single-workspace IDE

Qoder 1.0 splits workspace, execution, artifact, and delivery boundaries across isolated worktrees so parallel agent tasks stop colliding. Alibaba's own A/B data says its scoped memory engine cut input tokens by 40%.

2026-08-04

AI5 min read

Recherche en IA

Faible coût, pas d'échec : un correctif pour les agents de codage à 35 % du prix

CodeRescue, un système de routage de récupération pour agents de codage, utilise le retour d'exécution pour décider quand réessayer avec des modèles bon marché plutôt que d'escalader vers des modèles coûteux. Une couche de contrôle de risque conforme permet aux opérateurs de définir des objectifs de coût sans réentraînement, atteignant des taux de résolution quasi parfaits pour 35 % du coût de l'escalade systématique.

2026-07-25

Benchmarks & TestsFeatured3 min read

Agentic coding

Grok 4.5 just broke the coding agent leaderboard: the lead is real, the margins are tiny

Grok 4.5 now leads the SWE Marathon leaderboard, beating Claude 4 Opus and GPT-5. The benchmark tests real software engineering skills: bug fixes, feature additions, and code understanding across real repositories. The margin is slim, but the trend lines point toward a shrinking gap between what agents can do and what they need to do.

2026-07-20

Mistral AI3 min read

AI Agents

Mistral coding agents leave your laptop behind: parallel sessions, no hovering required

Mistral is moving coding agents to the cloud, enabling parallel, asynchronous task execution via the new Mistral Medium 3.5 model. The update introduces remote agents in Mistral Vibe and Le Chat, along with a Work mode for multi-step tasks, while keeping human oversight for sensitive actions.

2026-07-12

AIFeatured5 min read

Agent Benchmark Analysis

ProgramBench: every public AI scores 0% on the hardest coding test yet

ProgramBench challenges AI agents to reconstruct programs from binaries alone, without source code or issue descriptions. All public models fail to fully resolve any task, exposing weaknesses in probing, architecture, and stopping judgment. The benchmark is a stress test for coding agents moving beyond patch-based workflows.

2026-06-29

Benchmarks & TestsFeatured3 min read

Performance

Gemma 4 runs 90% faster in Ollama 0.31 with a trick that needs no config

Ollama 0.31 introduces multi-token prediction for Gemma 4 on Apple Silicon, achieving near 90% faster token generation on coding benchmarks. The speedup comes from an auto-tuned draft model and a custom MLX kernel that eliminates redundant weight reads.

2026-06-29