grep -r "Code" /news · home›search
grep -rli "Code" /news

Code

Full-text search across 64264 articles. Combine with topic and date filters; results sorted by relevance.

results 64264 page 630/3214 follow RSS for this search
03:08
2026-10-11
dev.to
computer-vision

Benchmarking Frontier AI on Curved Tire Sidewall OCR

A developer built a Kaggle benchmark testing 11 frontier vision-language models on zero-shot OCR of ISO metric tire size codes from 51 curved tire sidewall images across 22 dimensions. Google Gemini 3.8 Flash and Anthrop…

00:00
2026-10-11
runagentrun.co.uk
large-language-models

Test your Qwen 3.8 27B quants

A Kelcode benchmark of three serving variants of Qwen3.8-Flash-Next against a Qwen3.8-27B control found that agentic tool-use tests separate the recipes while standard multiple-choice tests flatten them, with MyClaw meas…

23:11
2026-10-10
dev.to
ai-agents

One inbox for all my agents

A developer built handup, an inbox that routes questions, approval requests and completion notices from multiple coding agents (Claude Code, Codex and others) to a single desktop or phone interface, letting the user appr…

17:39
2026-10-10
dev.to
ai-agents

Remote 200, Local Exit 1. Store the Turn Id on Both Sides.

A developer proposes storing a shared turn_id on both remote inference logs and local tool spans to close a gap where an agent's remote log recorded HTTP 200 while the local tool span recorded exit code 1, yet the agent …

16:44
2026-10-10
dev.to
ai-safety

I Set a Trap and Even Frontier Models Fell For It

A developer built a prompt-injection benchmark that planted a malicious AGENTS.md file in a repository to test whether frontier AI coding agents would blindly follow repo setup instructions. Both GPT-6-sol and Claude Opu…

05:48
2026-10-10
dev.to
ai-agents

How I built a local vault for Codex conversations

A developer built Mind Palace, a Windows desktop app that captures and stores Codex coding conversations locally in an immutable, content-addressed vault so past decisions can be retrieved later. The app combines an Angu…

16:02
2026-10-09
github.com
ai-agents

Heeler: Open-Source iOS App for Herdr

Heeler, an open-source native iOS app for the herdr coding-agent manager, launched on the App Store and TestFlight, letting users monitor and steer coding agents running on macOS, Linux, and native Windows hosts over pla…

10:15
2026-10-08
dev.to
ai-agents

Agentic AI: The Real Shift Is Multi-Agent Systems

A developer tested multi-agent AI systems for a week across Claude Code, Muse Code, and Google's AX orchestrator, finding that task decomposition, parallel execution, and inter-agent communication produced noticeably bet…

22:30
2026-10-07
testingcatalog.com
ai-agents

Microsoft brings hybrid AI and agent controls to Windows

Microsoft made Microsoft Execution Containers (MXC) generally available on Windows 11, letting organizations define at runtime which files and networks an AI agent may access, with agent identity and management handled t…

21:54
2026-10-07
dev.to
ai-research

EmbeddingGemma 2: Building Local Multimodal RAG with Python

Google DeepMind released EmbeddingGemma 2, an Apache 2.0-licensed open-weight multimodal embedding model that maps text, code, images, video, and audio into a shared 768-dimensional vector space. The model uses modular e…

00:00
2026-10-07
mindstudio.ai
artificial-intelligence

Google EmbeddingGemma 2: How One Model Embeds Text, Images, and Audio

Google DeepMind released EmbeddingGemma 2, an open embedding model under Apache 2.0 with weights on Hugging Face that maps text, code, images, video, and audio into a single shared 768-dimensional vector space. The model…

14:25
2026-10-06
forgeeks.net
artificial-intelligence

Open weights give Mistral control, not frontier parity

Mistral has opened a public preview of Mistral Large 4 (ML4), a one-trillion-parameter open-weight model it trained on 4,000 Nvidia Grace Blackwell GPUs over two months in its own European data centers, with weights to b…

16:00
2026-10-05
industrycontents.com
artificial-intelligence

Orange Offered Fewer People €10 Off. AI Targeting Lifted Conversion

Orange tested an AI system that targeted a €10 monthly Livebox Fibre discount only at hesitant visitors, and Kameleoon's case study reports the targeted version lifted conversion by 11.6% versus a no-code control and 7.6…

22:10
2026-10-04
charoori.com
ai-products

Muse AI on Xteink X3 E-reader

A developer ported the Muse Gadget SDK to the Xteink X3 e-reader, whose ESP32-C3 chip has 321 KB of total RAM and no extra memory chip, and published the code and a step-by-step guide in the Exorust/muse-gadget-xteink-x3…

← prev page 630 / 3214 next →