Imo this is along the lines of how talking to an LLM via text is like typing into a DOS Terminal and "GUI hasn't been invented yet" of some of my earlier posts. The GUI is an intelligent canvas.
LLMS
-
Gemini Nano Banana Pro Solves Exam Questions from Image
By
–
Gemini Nano Banana Pro can solve exam questions *in* the exam page image. With doodles, diagrams, all that. ChatGPT thinks these solutions are all correct except Se_2P_2 should be "diselenium diphosphide" and a spelling mistake (should be "thiocyanic acid" not "thoicyanic") :O
-
Gemini 3 Progress Rivals GPT-4 Breakthrough Moment
By
–
the Gemini 3 moment seems closer to GPT-4 than any other moment in recent times. So much progress released so suddenly that it's overwhelming. Especially NanoBanana's progress.
OpenAI around GPT-4 looked invulnerable , and Google looks invulnerable now with Gemini 3 (+TPUs -
GPT-5.1 Pro: Advanced AI Colleague with Enhanced Expertise
By
–
GPT-5.1 Pro: “feels like a step toward models that think and communicate more like real colleagues, with better domain expertise, intuition, and judgment, along with increased empathy and communication skill”
-
Google to Add NotebookLM Import to Gemini
By
–
Google is working on a new option to import notebooks from NotebookLM directly into Gemini. Gemini ecosystem
-
Using Claude and Gemini for AI-Assisted Development
By
–
this stack is insane for vibe coding: > Claude for backend & planning.
> Gemini for frontend & execution. -
Fundamental Limits of LLMs at Scale: Mathematical Foundations
By
–
10. Fundamental Limits of LLMs at Scale Establishes mathematical foundations for theoretical limitations constraining LLMs: hallucination, context compression, reasoning degradation, retrieval fragility, and multimodal misalignment.
-
LAMP: Language-Augmented Multi-Agent Reinforcement Learning Pipeline
By
–
9. LAMP: Language-Augmented Multi-Agent RL LAMP integrates natural language processing into multi-agent reinforcement learning through a three-stage pipeline.
-
Testing and sharing effective prompt engineering strategies
By
–
i know it's way more creative than me, i'm testing out different levels of prompts and sharing them with my audience. i share short and long prompts as well. sometimes long prompts perform better for a given use case, sometimes a short one will do.
-
Comparison of AI tool capabilities and API usage costs
By
–
it uses my API key, so I pay per token used. gemini app doesn't analyze videos the same way. I pay for gemini.