Discover AI Creator Profile

Gemini 3 PRO in 127 seconds

Discover AI November 19, 2025

2nd test on the causal reasoning capabilities of the new GEMINI 3 PRO. A different logic test - with GEMINI …

Gemini 3 PRO Logic: A BEAST!

Discover AI November 18, 2025

I performed my standard logic and causal reasoning test on the newly released GEMINI 3 PRO on the free platform …

Individualise your AI Companion: EASY

Discover AI November 18, 2025

The easiest way to individualize your AI - simple Demo. Please add additional personal guardrails to your individualized system prompt. …

SSR: Path-Factorized Self-Correction for LLMs

Discover AI November 17, 2025

An Old Trick from 400 BC for Next-Gen AI. All rights for SSR w/ authors: SSR: SOCRATIC SELF-REFINE FOR LARGE …

Beyond Transformer: Building an Artificial Mind

Discover AI November 16, 2025

All rights w/ authors: Intilligence Foundation Model: A New Perspective to Approach Artificial General Intelligence Borui Cai, Yao Zhao B. …

AI Learns in Low-Curvature Subspaces (RLVR)

Discover AI November 15, 2025

The success of Reinforcement Learning in fine-tuning LLMs presents a baffling paradox: despite immense computational cost, it achieves dramatic reasoning …

Reasoning TEST GPT-5.1: A Surprise

Discover AI November 14, 2025

A brand new GPT-5.1 has been released yesterday - and I test it with my causal reasoning test, that I …

World Model RAG: Generative Semantic Workspaces

Discover AI November 13, 2025

An ultra-modern RAG system with inherent world model creation and a structured, spaciotemporal memory. We've all seen LLMs fail on …

The Algebra of AI Thoughts: Self-Learn Reasoning?

Discover AI November 12, 2025

We often wonder if AI can truly teach itself to become smarter. It's a question that feels like it's straight …

Lean AI Reasoning: NEW Energy-Based Chain-of-Thought

Discover AI November 11, 2025

Optimizing Latent AI Thought Trajectories via Energy-Based Calibration. All rights w/ authors: OckBench: Measuring the Efficiency of LLM Reasoning Zheng …

AI Agents for Real-Time Intel: NEW Solution (Tsinghua, Stanford)

Discover AI November 10, 2025

Most advanced AI agents today operate on a fundamental flaw: they assume the world will politely pause while they think. …

Free RAG (File Search) w/ App dev by Google: TEST

Discover AI November 9, 2025

Notebook LM - Good News: Google launching the File Search Tool, a fully managed RAG system built directly into the …

The Geometry of AI Thoughts

Discover AI November 8, 2025

We've long treated LLMs as inscrutable black boxes. We see the final answer, but the intricate "thought process" leading to …

GPT-5 Nano Fails to Communicate w/ Agents

Discover AI November 7, 2025

Best Agent to Agent Performance Config. The Emergent Failure of Agentic AI. Singularity Paradox: Why AI Hive Minds are Failing. …

MultiModal Reasoning w/ Strong Oscillations (MIT)

Discover AI November 6, 2025

AI, AGI, SI: Harvard Univ, MIT and Tsinghua Univ examine the complexity of multi-modal reasoning AI models in more details …

Beyond Next Token Prediction: CALM AI

Discover AI November 5, 2025

Finally a new AI that implements the next generation after Next-Token-Prediction: CALM - CONTINUOUS AUTOREGRESSIVE LANGUAGE MODELS. All rights w/ …

AI's Reasoning Dark Matter Discovered

Discover AI November 4, 2025

All rights w/ authors: "Inverse Knowledge Search over Verifiable Reasoning: Synthesizing a Scientific Encyclopedia from a Long Chains-of-Thought Knowledge Base" …

SRL: NEW AI Training (by Google)

Discover AI November 3, 2025

All rights w/ authors: "Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning" Yihe Deng2*† , I-Hung Hsu1*, Jun Yan1, …

Geometric GROKKING Unlocked & Explained

Discover AI November 2, 2025

Given the latest insights on new geometric representations of knowledge patterns in the memory of Mamba or Transformer architecture, I …

AI's Secret Memory Discovered

Discover AI November 1, 2025

We Were Wrong About How AI Thinks. Newly published ArXiv pre-print raises the foundational question of when and how associative …

AI: New Graph-based Agent Planning (Tsinghua, CMU)

Discover AI October 31, 2025

Empower AI w/ Parallel Thoughts: NEW GAP Framework. All rights w/ authors: GAP: Graph-based Agent Planning with Parallel Tool Use …

The END of AI: Some Personal Reflections

Discover AI October 30, 2025

Just some personal reflections on the end of AI. Seen as a probability distribution. #artificialintelligence #scienceexplained #aireasoning

AI Is 96% Cheaper. You Can't Compete.

Discover AI October 28, 2025

We've all heard the promise: AI agents are now capable of performing complex human jobs, and the numbers are mind-boggling. …

Self-Learning AI: Prompts w/ Knowledge Graphs in ICL