Berlin Brown and Software Development

Big Claims, Real Limits There’s a lot of hype about AI right now. Some CEOs say AI has already surpassed human intelligence. Others claim it can replace all office work. Take this quote from OpenAI’s Sam Altman: “We are past the event horizon… The takeoff has started.” – Sam Altman, MarketWatch Interview (2025) He also wrote: “Robots are not yet walking the streets… we still can’t easily go to space, and there is a lot about the universe we don’t understand.” – Sam Altman’s Blog: The Gentle Singularity Bold stuff. But here’s my everyday, boots-on-the-ground experience. I’ve experimented with GitHub Copilot, DuckDuckGo AI, Agentic AI, Google’s AI tools, and I'm also building my own local LLM setup. I’d consider myself a layman when it comes to the deep internals of LLMs, but I use them regularly in a hands-on way. Good Uses of AI (So Far) AI tools work great for quick, well-scoped questions: “What’s 45 million divided by 100,000?” “How do I fix an SSL error in a Java HTTP...

 Here are some top courses and the impact to AI, so far not a big amount of change.  A couple of additions. Kind of reminds when I was school at UA, they added a Java source. See Georgia Tech and UA. https://catalog.gatech.edu/coursesaz/cs/ https://catalog.ua.edu/undergraduate/engineering/computer-science/courses/ CS 7545. Theoretical Foundations of Machine Learning. 3 Credit Hours. CS 7751. Probabilistic Graphical Models in Machine Learning. 3 Credit Hours. CS 7651. Human and Machine Learning. 3 Credit Hours. CS 7643. Deep Learning. 3 Credit Hours. Reinforcement Learning Computational Foundations of Machine Learning

 Elon Musk and Donald Trump feuding right now.

 I asked this into Chat GPT (source chatgpt question) "So when you look at current AI technology like LLM technology, it is currently, it is highly based on digital prompt inputs and analyzing large datasets with billions of parameters from text data.   The human brain does not necessarily operate that way.   What are current approaches to bridge the gap between low tech human brain processes to the machine learning algorithms with LLMs.  Projects like the numenta project and thousand brain project" Here is the response from chatgpt - source chatgpt model as of Jun5. "Recent AI research increasingly looks to the brain for inspiration. Neuroscience-derived ideas—such as sensorimotor learning, modular cortical columns, and memory consolidation—are being used to overcome limitations of today’s deep learning systems. For example, Numenta’s new Thousand Brains Project is an open-source initiative to build AI on cortical principles (sensorimotor input, grid-c...

 I remember some of these companies back in the day, now they are larger. I am going off memory: Google to Alphabet Yahoo to Yahoo Netscape - Didn't morph into Mozilla and Mozilla Foundation SmartBear - of Smartbear UI Fiddler to Fiddler AI 3dfx - bought out by Nvidia