GosuCoder Creator Profile

Gemini Flash 2.0 A 20-Year Developer's Honest Review After 40+ Hours of Coding

GosuCoder February 20, 2025

I've added Gemini Flash 2.0 as one of my 3 primary models I use daily for coding, and the reason …

Grok 3 Think is the first to do this in my testing!

GosuCoder February 19, 2025

Grok 3 Testing with and without Think. I'm actually really pleasantly surprised how good it is at one shot coding. …

Watching the Grok 3 Announcement

GosuCoder February 18, 2025

Grok 3 is suppose to be announced at 8:00pm PST, hoping for something awesome.

Grok 3 Announced - 10X More Training than Grok 2!

GosuCoder February 18, 2025

Grok 3 Announcement Summary My Links 🔗 👉🏻 Subscribe: https://www.youtube.com/@GosuCoder 👉🏻 Twitter: https://x.com/adamwlarson 👉🏻 LinkedIn: https://www.linkedin.com/in/adamwilliamlarson/ My computer specs GPU: …

Will AI Become a Superhuman Coder by 2025? The Future of Competitive Programming!

GosuCoder February 17, 2025

Competitive Programming is a great benchmark for LLM but it isn't indicative of what programming really is day to day. …

AI Keeps Enhancing Game Until They BREAK | Claude + GitHub CoPilot Test

GosuCoder February 16, 2025

Using Claude 3.5 Sonnet and Github Copilot in VS Code Insider, I ask the AI to keep making this game …

Qwen 2.5VL is an amazing model but impossible to run locally

GosuCoder February 15, 2025

Qwen 2.5VL is a Great model, but it seems impossible to run locally on AMD hardware at least. My Links …

AI reasoning without chain of thought, INSANE If true

GosuCoder February 14, 2025

This whitepaper on doing additional "thinking" in latent space has my head spinning a bit. Let me know your thoughts. …

AI is replacing this job INCREDIBLY FAST

GosuCoder February 13, 2025

I believe the Technical Writing Job will be hit first and hard as AI starts to become more and more …

o3-Mini is so close to being great | o3-Mini vs Gemini 2.0 Flash Experimental

GosuCoder February 12, 2025

O3 Mini and Google Flash 2.0 Experimental Thinking challenge each other in a newly updated series of questions. Both I …

AI makes it so EVERY Programmer has to be a Product Engineer or risk losing their job

GosuCoder February 11, 2025

This video I share something I've been thinking about a lot and that's how we as coders, programmers, and engineers …

I Tested Gemini Pro & FLASH 2.0...and I'm SPEECHLESS

GosuCoder February 10, 2025

The new AI models Gemini Flash 2.0 and Gemini 2.0 Pro Experimental are better than I thought they would be. …

What really are AI agents? Simply explained

GosuCoder February 9, 2025

AI agents are widely misunderstood, with many people mistakenly calling simple API calls 'AI agents' when they lack true decision-making …

GitHub Copilot AI Agent replaces expensive software in under 2 hours

GosuCoder February 8, 2025

I decided to see if I can replace paid for AI Note Takers with my very own, that I run …

GitHub Copilot Agent Mode is WAY BETTER than I expected!

GosuCoder February 7, 2025

GitHub Copilot Agent Mode is actually incredibly good. I tested it for hours, and wanted to share some of my …

3 Things Claude 3.5 Sonnet Does Better than Everyone Else | Pure MAGIC

GosuCoder February 6, 2025

3 things that I can't live without thanks to Claude 3.5 Sonnet, plus some recognition of how good Claude 3.5 …

Run AI Models on Your PC: Best Quantization Levels (Q2, Q3, Q4) Explained!

GosuCoder January 9, 2025

The video is about quantization in large language models, explaining what it is, how it works, and the trade-offs between …

Project Digits is the Most Exciting Announcement at CES

GosuCoder January 8, 2025

The video is about Nvidia Project Digits, a compact desk-sized AI supercomputer powered by the Nvidia Grace Blackwell super chip, …

Gemini Flash 2.0 Experimental A 20-Year Developer’s Honest Review for coding

GosuCoder January 7, 2025

The reviewer shares their experience with Gemini Flash 2.0 Experimental, a 20-year developer's honest review. They compare it to Deep …

Can LLMs Play Chess | DeepSeek vs Claude vs OpenAI o1

GosuCoder January 6, 2025

The video discusses the capabilities of Large Language Models (LLMs) in playing chess, comparing DeepSeek, Claude, and OpenAI o1. The …

GosuCoder