Better than Deepseek?!, Claims new GSI Lab "Deep Cogito"!

releasing the strongest LLMs of sizes 3B, 8B, 14B, 32B and 70B under open license. Each model outperforms the best available open models of the same size, including counterparts from LLaMA, DeepSeek, and Qwen, across most standard benchmarks. In particular, the 70B model also outperforms the newly released Llama 4 109B MoE model.
The LLMs are trained using Iterated Distillation and Amplification (IDA) - a scalable and efficient alignment strategy for general superintelligence using iterative self-improvement.
Each model can answer directly (standard LLM), or self-reflect before answering (like reasoning models).

🔗 Links 🔗

Ollama Cogito 3b - https://ollama.com/library/cogito:3b

https://huggingface.co/collections/de...


❤️ If you want to support the channel ❤️
Support here:
Patreon -   / 1littlecoder  
Ko-Fi - https://ko-fi.com/1littlecoder

🧭 Follow me on 🧭
Twitter -   / 1littlecoder  

로딩 중...

Better than Deepseek?!, Claims new GSI Lab "Deep Cogito"!

OpenAI Sora First Impression - 40+ Examples | Will This Change Video Forever?

POV You're Searching For GPT-5 #ai #gpt5 #skit

Gemini 3.0 Pro (Lithiumflow & Orionmist - Tested): This Checkpoint of Gemini 3 is PRETTY GOOD!

Google's Gemini 2.0 AUTOMATOR: This AI Agent CAN Automate ANY REPETITIVE TASKS!

[10분 테코톡] 제프리의 ChatGPT 답변 생성 원리

Remote Code Execution on Bank Loan Calculator (Python eval()) — picoCTF 3v@l