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

Code

Full-text search across 68697 articles. Combine with topic and date filters; results sorted by relevance.

results 68697 page 1135/3435 follow RSS for this search
10:07
2026-10-12
arxiv.org
artificial-intelligence

Oído: Open-Vocabulary Speech Recognition on a $5 Microcontroller

Researchers submitted Oído, an inference engine that runs open-vocabulary English speech recognition entirely on a $5 ESP32-S3 microcontroller with no neural accelerator, executing a 13M-parameter Conformer-CTC model wit…

09:39
2026-10-12
theagenticleaderboard.com
ai-agents

dsh-our-free-model: 10,433 stars in 18 days

Cline ranked #1 among 100 evaluated agents with a score of 87.8 in the week of 2026-10-12, according to the weekly agent rankings. Deepseek-harness posted the largest drop, falling from rank 16 to rank 100 (-84), while n…

02:58
2026-10-12
dev.to
ai-tools

Bro Saw Two Photos and Made Up Lore

A developer built UNSEEN, a walking game that uses a local open-weight vision model (Qwen3-VL-2B-Instruct via Ollama) only to describe photos as structured data, while deterministic code — an "evidence gate" — decides wh…

00:00
2026-10-12
vercel.com
ai-agents

Muse Wonder now available on AI Gateway

Meta's Muse Wonder model is now available on Vercel's AI Gateway under the model name meta/muse-wonder-1.0, giving developers access without a separate Meta account. The model targets coding, long-running agents, and com…

19:00
2026-10-11
lord.technology
artificial-intelligence

The clones are coming home

ArtCraft's Brandon Thomas is using Claude to build open-source Rust recreations of Adobe and Microsoft Office applications, including PhotoCraft, WordCraft, GridCraft and DeckCraft, with PhotoCraft's 11 October roadmap r…

15:18
2026-10-11
dev.to
large-language-models

Anthropic Model Names and Deprecations: Build a Changelog Habit

A developer outlines a changelog habit for managing Anthropic model identifiers, arguing that hardcoded model strings scattered across application code, Terraform variables, CI secrets and dashboards create avoidable out…

11:20
2026-10-11
dev.to
ai-agents

I built an agentic workforce where done means a command exited 0

A developer built Crew, an open-source plugin for Hermes Agent that replaces an AI coding agent's self-reported "done" status with a frozen verification command that must exit 0 before a task card can close. The system a…

08:37
2026-10-11
dev.to
ai-research

To Retry or Not to Retry? That Is the Question.

A developer built a Kaggle Benchmarking Challenge submission that tests AI models on a single resilience question: whether an HTTP request should be retried after a failure. The benchmark probes whether models understand…

06:18
2026-10-11
dev.to
ai-agents

I built a cookie bridge, then changed my entire agent setup

A developer built Browser Cookie Bridge, a macOS app that transfers cookies from Chromium browsers like Brave into AI coding agents' in-app browsers so agents can start from existing logged-in sessions. After hitting RAM…

00:42
2026-10-11
dev.to
ai-tools

ElevenLabs vs Google Cloud TTS: Developer Comparison

A developer comparison of ElevenLabs and Google Cloud Text-to-Speech finds ElevenLabs delivers higher-fidelity, more expressive neural voice output with instant voice cloning from as little as 10 seconds of audio, while …

22:42
2026-10-10
dev.to
generative-ai

Leaf Pixels

A developer built Leaf Pixels, a Next.js app that uses two open-weight models to turn any picture into a printable 24×24 colour-by-letter pixel-art sheet for kids to colour outside. The pipeline has gpt-oss-120b on Groq …

17:53
2026-10-10
breadbowl.ai
artificial-intelligence

Using KV cache as embeddings

BreadBowl-Embed, released under Apache-2.0 with open weights, introduces a late-interaction embedding architecture that stores every passage as 16 routing-value slots rather than one vector per document or one per token.…

← prev page 1135 / 3435 next →