Nov 24UpscalingTrying out Midjourney’s new upscaling feature has impressed me! The new functionality can double and quadruple the original resolution of a generated image, making it possible to get incredibly fine detail of images. Here’s an example of a prism…Midjourney2 min readMidjourney2 min read
Nov 19It’s No Longer Dotty, It’s PoppyIn terms of pushing ubiquity of voice-first devices, Amazon has invested significantly and likely much more than any other competitor over the past decade. One of these pushes was in the form of the Echo Dot, that drove the price of first party Amazon hardware with voice interaction to incredibly…Echo2 min readEcho2 min read
Nov 14Analyzing and RegenerateWorking with ChatGPT a bit recently, I was frustrated with a few failures when it would spend a significant time “Analyzing…” only to fail. When it retried, I was beyond elated but started to become frustrated when two additional attempts failed. Then, I was tempted with the button “Regenerate”. Of…UX1 min readUX1 min read
Nov 10Version 3 is Always the BestIn applying my own advice, I found that when asking ChatGPT to create three versions and then assess them, version 3 is always the best when it’s being asked to rate its own performance as it’s producing a prompt sequentially. Interesting. This is almost a very human way of doing…ChatGPT2 min readChatGPT2 min read
Nov 9Ask for MoreSometimes, we’re too polite. This is especially the case with generative AI. The prompts we ask AI are usually the same as what we’d ask a skilled person in a topic. “Write a five paragraph essay with arguments about…” and such. Sure, you can add more details but the issue…Generative Ai2 min readGenerative Ai2 min read
Nov 8GPTs’ Discovery ProblemOpenAI might have a problem similar to Alexa Skills and Actions on Google… discovery. With the opening of the platforms to developers to create and publish their own flavours of the language models, people will now be able to select specialized task-oriented bots to work with. The issue will be…OpenAI2 min readOpenAI2 min read
Nov 7Too Much but the SameIn a time of crisis, some of the problems of mainstream media coverage are: The lack of details The slow pace at which the information is updated The clutter of ads that break up the information Over the past month, I’ve found myself doom scrolling on major news outlets, desparately…News2 min readNews2 min read
Nov 6The Wimmelbook TestA few weeks ago, I finally was able to try OpenAI’s new DALL-E 3’s image generation tools. My standardized test is to use a prompt that generates a wimmelbook (e.g. Where’s Waldo? style) image. I love these books and as a child, could get lost in the complexity, seeing all…Generative Ai3 min readGenerative Ai3 min read
Nov 5The Narrow BridgeI haven’t felt much like writing lately. I uploaded my last post while on an Air Canada flight from Tel Aviv to Toronto, coincidentally, on October 7. Thanks to inflight WiFi, the breadth of the horror that was unfolding was slowly being made apparent and when I landed 11 hours…Hope3 min readHope3 min read
Oct 7Government ServicesA few days ago, I needed to do a transaction that required filling transferring ownership. It’s been more than a decade and usually such a transaction required that I go to a government office, take a number, and wait in line. Then after I’ve filled out a form, it’s then…Internet Services1 min readInternet Services1 min read
