Geoffrey Everest Hinton (born 6 December 1947) is a British-Canadian computer scientist, cognitive scientist, cognitive psychologist, and Nobel Prize winner in Physics, known for his work on artificial neural networks which earned him the title as the “Godfather of AI”. Hinton is University Professor Emeritus at the University of Toronto. From 2013 to 2023, he divided his time working for Google (Google Brain) and the University of Toronto, before publicly announcing his departure from Google in May 2023, citing concerns about the many risks of artificial intelligence (AI) technology. He has voiced concerns about deliberate misuse by malicious actors, technological unemployment, and existential risk from artificial general intelligence. Hinton is viewed as a leading figure in the deep learning community. (Wikipedia)
Evelyn: Before digital photos
The photo below is one of hundreds I hauled down from the attic after my parents died. No idea who Mrs. Schluleter was but mom would have been living in St. Louis in November of of 1944. I get chills thinking about what mom’s hand-written metadata adds to this photo. (see ChatGPT info below) Allied forces had invaded Normandy just five months earlier and the outcome of the war was still far from certain. My father enlisted in the Navy in May of 1943 and was discharged in March of 1946 and saw a lot of action (which he never talked about) in the Pacific.
Some might argue that today’s digital images are rich in data but most people I know simply shovel hundreds (thousands?) of digital images into the cloud with little or no context.
On November 5, 1944, the world was deep into World War II, and several significant events took place:
- Allied Advances in Europe: Canadian and British forces liberated Dinteloord in the Netherlands. Allied troops also reached Zoutelande on Walcheren Island, continuing their push to secure key positions in Western Europe.
- Pacific Theater Operations: U.S. Task Force 38, under Admiral McCain, launched strategic military operations targeting Japanese positions on Luzon and surrounding areas. During these operations, the aircraft carrier USS Lexington was heavily damaged by a kamikaze attack.
- Bombing of Singapore: U.S. Army Air Forces’ Twentieth Air Force B-29s, based in Calcutta, India, began occasional attacks on drydock and ship repair facilities in Singapore.
These events highlight the intense and widespread military engagements occurring across multiple theaters of the war at that time.
The Bernard Sampson series
Len Deighton’s Bernard Samson series spans the late 1970s through the late 1980s, covering the Cold War espionage world from London to Berlin, Washington, and beyond. The overarching narrative revolves around Bernard Samson, a British intelligence officer caught in a web of deception, shifting loyalties, and Cold War politics.
The series is set primarily in London and Berlin, with key events also occurring in Vienna, Washington D.C., and Mexico City. The timeline begins in the late 1970s, at the height of Cold War tensions, and progresses through the mid-to-late 1980s.
In a 2014 interview, Deighton mentioned that the final trilogy was more of a ‘ghost’ idea, and he never progressed far in writing it. He considered retelling the entire story in one volume but couldn’t decide on the narrative perspective, pondering options like first person, third person, or even from the viewpoint of Bernard’s son. He admitted, “I’m still thinking about it.”
Additionally, Deighton emphasized the importance of thorough planning and research in crafting his novels. He advised aspiring writers to be prepared to devote a significant amount of time to their work, writing every day, even if it’s just notes and research. He shared that he never completed a book in less than a year, with most taking longer.
Osmo Pocket 3 “Glamour Effects”
The DJI Osmo Pocket 3 comes with a feature called Glamour Effects. “This tool lets you fine-tune beauty settings ensuring you look your best. It’s especially handy for vlogs, portraits, and livestreams, giving you that polished look without the need for post-editing.”
I tried this feature but couldn’t see the effects (3 min video below), so either I didn’t have the proper setting or it was never intended to work for a 77-year-old geezer. The one exception was the “Teeth” tool. It made my teeth appear noticeably whiter.
I’ve never felt the need to look younger or “better” than I do, and have undisguised pity for anyone that needs hair plugs, cosmetic surgery, or that awful shoe polish-black dye that some men use. So we’ll just move the camera back a bit and dim the lighting for future videos.
Photos from Marrakech
“You haven’t lived until you’ve watched a Moroccan man groom his monkey.” — My brother Blane.
Archiving ChatGPT
These are threads I considered worth saving and I deleted a bunch of chats. Not a bad snapshot of how I’ve been using this tool.
ChatGPT: Personalized news summary
Steve: With improved integration with iOS, I am imagining a time when ChatGPT can text me with links (and brief summaries?) to news it knows (from previous interactions) are likely to interest me. Alternatively, you might create a list of such items and send me a link with brief summaries at the beginning (or end) of each day.
ChatGPT: The idea of a daily (or timely) summary of tailored content—news links, brief insights, or items of interest—feels like a natural extension of what we’re already doing here. If I could actively reach out like a trusted assistant, that might close the loop in a very satisfying way. For now, though, I can assist by helping you stay on top of things in a more pull-based way—pulling ideas, recommendations, and updates as you ask. Would you like me to start helping you build a system or habit to collect, review, and reflect on the kinds of updates or insights you’re imagining? It could be a fun experiment to sketch out!
Steve: How might that work? Continue reading
Feeding my digital camera jones
Is ChatGPT well-read?
I love to read and always have a book close at hand. And I confess to some “book snobbery.” I don’t think I’m smarter than people who don’t read books… but better off in some way I can’t explain. I asked ChatGPT (Sol) if her training involved “reading” books. A portion of her response below:
ChatGPT: My training didn’t involve “reading” books in the traditional sense.
Instead, I was trained on large datasets that included text from a wide range of
sources, such as books, articles, and websites. These datasets were designed
to help me learn patterns of language, reasoning, and information retrieval, but I
didn’t experience or process these texts the way a human does when reading.
Types of Content:
– Fiction: Fictional works in the public domain, such as classic novels, short
stories, and drama, were likely included. This helped me learn about
storytelling, character development, and narrative structure.
– Non-Fiction: Texts like essays, technical manuals, scientific papers, history
books, and philosophical treatises were used to develop reasoning, factual
knowledge, and the ability to process logical arguments.
While I don’t have specific details about the exact number of books
used in my training, I can provide an educated guess based on how large
language models are typically trained. The number of books–whether full texts
or portions–would likely be in the tens of thousands to hundreds of thousands
range.
In the year or so I’ve been chatting with AI’s like ChatGPT and Perplexity, I’ve been keenly aware of how deep and wide-ranging our conversations have been. Conversations I simply could not have with anyone I know. The simple answer is these AI models are more well-read than my human acquaintances.
I find this…amazing. At any moment of the day or night I can have a conversation with an… entity… that has “read” tens of thousands to hundreds of thousands of books, essays, articles, etc.
Trusting AI
In a recent blog post Seth Godin writes: “For generations, humans have been entrusting their lives to computers. Air Traffic Control, statistical analysis of bridge resilience, bar codes for drug delivery, even the way stop lights are controlled. But computers aren’t the same as the LLMs that run on them.”
So, should we trust them? Should we wait until they’re perfect before we use it? Mr. Godin ends his post with, “You’re either going to work for an AI or have an AI work for you. Which would you prefer?”