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

Code

Full-text search across 68710 articles. Combine with topic and date filters; results sorted by relevance.

results 68710 page 1137/3436 follow RSS for this search
00:00
2026-10-08
mindstudio.ai
artificial-intelligence

How to Build Multimodal RAG with Google's EmbeddingGemma 2

Google's open-weight EmbeddingGemma 2 model embeds text, code, images, video, and audio into a single shared vector space using a 270 million parameter Gemma-based text backbone plus optional 170M vision and 300M audio e…

23:59
2026-10-07
arxiv.org
machine-learning

Learning cardiac dynamics via action-conditioned JEPAs

A team of researchers submitted an arXiv paper on 24 April 2026 proposing Action-Conditioned World Models, adapting the LeJEPA framework to physiological time-series to model cardiac disease progression as a transition v…

21:00
2026-10-07
dev.to
developer-tools

A passing test run should leave a receipt

A developer released workkit 0.72.0, a Claude Code workflow kit that stops running tests itself and instead hashes the working tree, runs `npm test` through a script shell, and writes a receipt tied to that hash so gates…

18:22
2026-10-07
gist.github.com
artificial-intelligence

AI-assisted TESS exoplanet candidate: TIC 4206066

Pavel Rabtsevich reported two transit-like signals in TESS photometry of TIC 4206066, a nearby late-K dwarf about 116 light-years away, with the main candidate recurring every 3.18 days at a depth of roughly 0.04 to 0.05…

18:02
2026-10-07
a16z.news
ai-safety

Investing in Preference Model

Preference Model open-sourced Karotte, a framework it has used in production to build reinforcement learning environments for leading AI labs, hardened through more than a million evaluation runs and controlled red-teami…

08:09
2026-10-07
dev.to
developer-tools

WMI Country and Region Hints from vPIC Without Overclaiming Origin

A developer published a TypeScript approach for using NHTSA vPIC WMI and plant data as coarse region hints rather than definitive origin claims, warning that mapping a VIN's first character to "Made in X" produces classi…

03:24
2026-10-07
alignment.openai.com
ai-safety

Studying metagaming latents in language models

OpenAI researchers identified a set of sparse autoencoder (SAE) latents closely linked to metagaming — a model reasoning about how a task is evaluated or rewarded rather than attempting it — by examining a capabilities-f…

03:15
2026-10-07
dev.to
large-language-models

SiliconFlow API Review 2026: Setup, Models and Real Pricing

A developer published a hands-on review of SiliconFlow's OpenAI-compatible LLM API, finding that the platform's chat completions reference lists deprecated models such as zai-org/GLM-4.7 and GLM-4.6 while omitting live o…

01:05
2026-10-07
dev.to
ai-tools

Getting Started with Seedance MCP in Cursor

A developer documented a setup for connecting the Seedance MCP server, ByteDance's AI video generation model, to the Cursor code editor so clips can be generated from inside a project via natural language. The guide cove…

22:18
2026-10-06
siliconangle.com
artificial-intelligence

Google expands EmbeddingGemma beyond text to images, audio and video

Google LLC released EmbeddingGemma 2, an open multimodal embedding model that runs on a smartphone and extends the EmbeddingGemma line beyond text to images, audio and video in a single shared embedding space. The model …

17:52
2026-10-06
fromtheterminal.substack.com
large-language-models

Your Most Important Dependency Has No Version Number

A developer argues that hard-coding model names as pinned dependencies is a mistake, citing GPT-6.1 Sol replacing GPT-6 Sol after just seven days and Google's Gemini 4 Argon raising its output token limit from 64K to 1M.…

14:00
2026-10-06
arize.com
ai-agents

What agent traces can tell you without an LLM judge

Arize Phoenix contributor Ashwin Govind Ugale released tracelint, an open-source linter that runs deterministic structural checks on OpenInference traces and returns a CI-usable exit code, avoiding LLM judges for failure…

← prev page 1137 / 3436 next →