Tech Tips, Tricks & Trivia

This Week I Learned -  * Building on the foundation of Gemini 1.0 and 1.5, Gemini 2 is designed for the “agentic era,” enabling AI systems to understand, reason, and act more effectively in a variety of contexts. Gemini 2 Flash introduces a new Multimodal Live API, enabling real-time audio and video-streaming input for dynamic application development.  * OpenAI's o3 family of reasoning-focused AI models employ advanced techniques like reinforcement learning and “private chain of thought” processes to simulate step-by-step logical thinking.  * Sora is OpenAI's advanced AI model developed to create realistic videos from textual descriptions. Sora Turbo, is now available as a standalone product at Sora.com, exclusively for ChatGPT Plus and Pro users.  * Amazon Nova is a collection of advanced AI models introduced by AWS as part of its Bedrock AI platform. The Nova lineup includes several models, each catering to specific use cases. Amazon Nova Micro is a text-only ...

Github Copilot simplifies coding, moving away from complex syntax towards the intuitive use of natural language. Anyone who wants to be a developer has to declare as a specific statement what they want to build in a code editor like Visual Studio with Github Copilot extension installed and this amazing code assistant will be ready to assist. When a developer begins typing, Copilot uses its AI model to predict and suggest potential completions for the code. These suggestions appear in gray as ghost text , indicating that they are not yet part of the actual code. A developer can then accept the suggestion by pressing the tab key, instantly incorporating the ghost text into their code. In this TED talk from April 2024, Thomas Dohmke, the CEO of GitHub, explains in simple terms & also demonstrates how  With AI, Anyone Can Be a Coder Now  - Sound bites: "The age of programming has been reborn."   - Github Copilot has a transformative impact on software develop...

In the first episode of the The Pragmatic Engineer podcast (24-September-2024) featuring Simon Willison , the co-creator of Django & creator of Datasette (an open-source tool for exploring and publishing data) discusses his extensive experience using large language models (LLMs) for coding.   Willison shares his initial awe and subsequent apprehension about LLMs' potential to replace programmers, highlighting both the immense productivity gains and the ethical considerations involved.  He details his current LLM workflow, emphasising the importance of learning how to effectively prompt and utilise these tools rather than focusing solely on theoretical understanding.   Finally, he offers advice for both experienced and junior engineers on leveraging LLMs to enhance their productivity and future-proof their careers. Highlights - Gergely Orosz : I'm interested in how AI development helps your specific workflow and where it doesn't. You had a really interesting ...