More from Matt Mazur
At the end of 2022 I wrapped up my contract work with Help Scout and took the plunge to work on my indie software businesses full time. I’m now two years into that adventure, and wanted to share a periodic update about how things are going. Preceden on the Back Burner I made 32 commits … Continue reading 2024 Year in Review →
It’s been a few months so I wanted to say hey to the 7 of you who follow this blog and share a few updates about what I’ve been up to. Quick recap At the start of 2023 I quit consulting to go full time on Preceden, my SaaS timeline maker, after growing it on … Continue reading It’s Time to Build →
At the beginning of 2023 I went full time on Preceden, my SaaS timeline maker business, after 13 years of working on it on the side. A year has passed, so I wanted to share an update on how things are going and some lessons learned. Preceden My main focus in 2023 was building AI … Continue reading Reflecting on My First Year as a Full Time Indie Founder →
Below are the steps I used to get Mistral 8x7Bs Mixture of Experts (MOE) model running locally on my Macbook (with its Apple M2 chip and 24 GB of memory). Here’s a great overview of the model for anyone interested in learning more. Short version: The Mistral “Mixtral” 8x7B 32k model,developed by Mistral AI, is … Continue reading Running Mistral 8x7Bs Mixture of Experts on a Macbook →
One of the many new features announced at yesterday’s OpenAI dev day is better support for generating valid JSON output. From the JSON mode docs: A common way to use Chat Completions is to instruct the model to always return JSON in some format that makes sense for your use case, by providing a system … Continue reading Experimenting with GPT-4 Turbo’s JSON mode →
More in AI
Parenting a Newborn with AI Is Radically Different from a Few Years Ago
Early in the coronavirus pandemic, as I sat at home channeling my anxiety into publishing daily essays on this newsletter (a streak I kept up ... Read more The post In Search of the Deep Life appeared first on Cal Newport.
Prefix caching helps coding agents stay fast as conversations grow. Prompts, tool calls, and inference routing determine how much work the model can reuse.
The tool we created to build understanding and mastery for our own internal work at Answer.AI
Internalize this graph, we post it on this blog a lot. If trends continue, China will have 10x the electricity of the US in 10 years. Whenever you think about geopolitical strategy, always keep it in mind, because whatever your plans are must consider this. Here’s a strategy that would make sense for America long term. Sell as many AI chips into China as possible, use the money to purchase solar panel and battery factories, and build out electricity capacity as quickly as possible. Fundamentally, compute is a function of electricity. That’s the sort of long term thinking that gives America a chance. With robotic labor, immigrants like Jensen and Elon, a business friendly culture, and an incredible chunk of land, it’s not so clear who is ahead in 50 years. Regardless, I do know this strategy would lead to massive prosperity for the citizens of both countries. However, that’s not close to what we see happening. We see a lot of short term zero sum thinking in action. It’s very scary what the US “AI race” mentality leads to. When exactly does the race end? Whatever capabilities you have today will eventually be matched, unless… …you believe that you can use ASI in a decapitating first strike. I’m worried that this is what these people see as the only way out. It probably doesn’t work, can you outthink steel and drone production? I don’t see how, see my critiques here. But I’m not totally sure, I’m not a superintelligence. And if it does work, that may be the end. My likelihood of imminent WWIII went up a lot with the nationalization of NVIDIA.