English · Not set Change ▾

Language Location Show all languages

Live scores ticker: On · Turn off

Markets ticker: On · Turn off

Saved in a cookie on this device (and in your account when you are logged in). We never store your IP address.

Entities › name

M-parameter

2 headlines · 2 outlets · 2026-10-06 → 2026-10-08 · Wikipedia ↗ · 🔒 Follow

Latest coverage

Dev.to ·17h ago ☆

Community aggregator
Country: United States

Tiny model. Big decisions. — How I built a 144M-parameter typed decision model that routes 82% of agent decisions off LLMs

Tiny model. Big decisions. — How I built a 144M-parameter typed decision model that routes 82% of agent decisions off LLMs Or: why your agent's "should I run this command?" does not need a 70B chat model. Every agentic workflow I build hits the same wall: the interesting logic is 10 lines, and the…

AI Technology Details Archived copy ↗

Techmeme ·Oct 6, 2026 ☆

Aggregator
Country: United States

Google DeepMind launches EmbeddingGemma 2, a 740M-parameter model to map code, images, video, and audio in a shared embedding space, under an Apache 2.0 license (Google)

Google : Google DeepMind launches EmbeddingGemma 2, a 740M-parameter model to map code, images, video, and audio in a shared embedding space, under an Apache 2.0 license — EmbeddingGemma 2 is the most capable model for on-device multimodal embeddings, natively mapping combinations of text, images …

AI Technology Details Archived copy ↗

M-parameter

Latest coverage

Tiny model. Big decisions. — How I built a 144M-parameter typed decision model that routes 82% of agent decisions off LLMs

Google DeepMind launches EmbeddingGemma 2, a 740M-parameter model to map code, images, video, and audio in a shared embedding space, under an Apache 2.0 license (Google)

Explore

News

Watch & listen

Understand

Explore

Join

Banana News

Upgrade to unlock this

Keyboard shortcuts

Move

Go

Everywhere