Novi AI

non-profit

Activity Feed Request to join this org

AI & ML interests

We make SLMs.

Recent Activity

GGUFGuy updated a model 1 day ago

Novi-AI/model-progress

GGUFGuy published a model 1 day ago

Novi-AI/model-progress

GGUFGuy updated a model 9 days ago

Novi-AI/Novi-Pico-Base

View all activity

DedeProGames

posted an update about 19 hours ago

Post

945

🚀 Introducing OpenWork — Deploy agents everywhere.

OpenWork is an open-source AI agent workspace built on top of OpenCode.

Deploy autonomous agents, schedule tasks, manage projects, and let AI work for you — directly from your terminal.

Features:

- 🤖 Deploy autonomous AI agents
- 📅 Schedule recurring tasks
- 🧠 Persistent memory and workspaces
- 🔌 MCP integrations and custom tools
- 📥 Agent Inbox and task management
-⚡ Support for local and cloud AI models
- 🖥️ Interactive terminal interface (TUI)

Your agents. Your models. Your workflow.

Fully open-source. MIT licensed.

⭐ GitHub: https://github.com/dedeprogames-official/openwork

#OpenSource #AI #AIAgents #OpenWork #OpenCode

GGUFGuy

updated a model 1 day ago

Novi-AI/model-progress

Updated 1 day ago

GGUFGuy

published a model 1 day ago

Novi-AI/model-progress

Updated 1 day ago

DedeProGames

posted an update 5 days ago

Post

3999

Im working on a 23M ASR model, trained on 100k hours of audio

5 replies

DedeProGames

posted an update 9 days ago

Post

5825

how is this possible

13 replies

GGUFGuy

updated a model 9 days ago

Novi-AI/Novi-Pico-Base

287k • Updated 9 days ago • 287 • 1

Bc-AI

in Novi-AI/Novi-510x 9 days ago

Hmmmm

#2 opened 10 days ago by

Bc-AI

GGUFGuy

in Novi-AI/Novi-510x 9 days ago

Hmmmm

#2 opened 10 days ago by

Bc-AI

DedeProGames

in Novi-AI/Novi-510x 9 days ago

Hmmmm

#2 opened 10 days ago by

Bc-AI

DedeProGames

posted an update 12 days ago

Post

6286

🧱 SLM Tetris Arena: can a small language model play Tetris without ever being trained on it?

I built an arena where tiny decoder-only LMs (50K–250M params) play Tetris zero-shot. There is no fine-tuning and no game data. They only use what they picked up from pre-training on text.

How it works:
- For every piece, the engine simulates each legal placement and describes the result in plain English ("clears one line, creates no new holes, keeps the stack low…").
- The model never sees the grid. It reads each description, and the arena compares log P(" good move") with log P(" bad move"). The best-rated placement is played.
- Every player gets the same piece sequence, so it's a fair race.
- There are two protocols: Guided (the rules are in the prompt) and Blind (no rules, only pre-training knowledge).

Two ways to play:
- Match: pick any models (even your own, custom architectures welcome) and watch them play side by side on retro 8-bit boards.
- Ranked: press Play and the arena picks up to 4 models at random from a curated pool of 29. Nobody chooses their opponents, so Elo can't be farmed. Matches run on the server and count even if you close the tab.

First results (~225 ranked matches):
- gpt2 (124M) leads with 1283 Elo, but SupraNeo-4M (4M) is right behind at 1239. Next come LowOnMind-5M and BananaMind-2.1-Pico (1.5M!).
- Model size barely predicts Elo (r ≈ 0.06). Survival does (r ≈ 0.9): the models that avoid holes and keep the stack low are the ones that win.

Every ranked match (seed, model commit SHAs, scores, Elo before/after) is logged in a public dataset.

▶ Play: DedeProGames/SLM-Tetris-Arena
📊 Results: DedeProGames/lm-tetris-arena-results

Want your model in the Ranked pool? Drop it in the comments!