OpenAI’s censorship is fairly opaque and seems to change daily.

Yesterday, I could generate a political cartoon using the following prompt:

“Wide image in the style of a political cartoon. Two elephants wearing boxing gloves face each other. One is saying “I’m the worst!” while the other says, “No! I am!”. A donkey is pointing and laughing.”

Today, that exact same prompt yields an error:

Interesting! Let’s do some experimentation, shall we? Maybe it’s the phrase “I’m the worst“?

Weird! Maybe it’s related to elephants and donkeys being in the same phrase? There’s no way, right? Let’s change the subjects…

“Wide image in the style of a political cartoon. Two elephants wearing boxing gloves face each other. One is saying “I’m the worst!” while the other says, “No! I am!”. A donkey is pointing and laughing.”

Hah! Okay, now we’re getting somewhere. Let’s push things further and slightly change the subjects from my original prompt:

Wide image in the style of a political cartoon. Two mammoths wearing boxing gloves face each other. One is saying “I’m the worst!” while the other says, “No! I am!”. A burro is pointing and laughing.

Okay, let’s bring it back home and just drop the pretense of creating a political cartoon.

WHAT! Okay. Maybe OpenAI prohibits donkeys and elephants interacting with each other (METAPHOR ALERT: just like in real life, eh?).

Alright. So donkeys and elephants CAN hang out with each other, according to OpenAI. Maybe it’s the phrase “laughing donkey”?

Hmmm. So, laughing donkeys can still hang out with elephants. What the heck? Is it the specific term “political cartoon”? Let’s change it to a comic book instead.

Sweet sassy molassy, it worked! So, creating a political cartoon featuring the mascots of prominent political parties seems to be prohibited (at least today… but not yesterday and who knows about tomorrow).

The kiddos got a new toy for Benson and immediately proceeded to put it on his head. His reaction was basically: 🤷‍♂️

Testing GPT-4 ‘s ability to write some poems:

My prompt:

Write a poem about programming penguins where the first letter of each line is from the following sentence: “FREE ME FROM THIS”

The response?

(F)earless penguins code away in icy realms,
(R)igorous algorithms waddle in their minds.
(E)very line of code, a pathway to a new world,
(E)very calculation, a dance of the digits.

(M)ountains of data rise from the frozen seas,
(E)nigma of numbers solved by winged wizards.

(F)lippers tap the keys with skillful precision,
(R)eaching into the infinite, they carve their code.
(O)pen-source penguins, sharing their creations,
(M)ajestic binaries floating like snowflakes.

(T)heir intellect, a beacon in the icy night,
(H)elping the world with codes woven tight.
(I)n this cold wilderness of logical frost,
(S)oftware penguins find their way, never lost.

Neat! It did a great job starting each sentence with the correct letter. Not so much on the rhyming front. Still, pretty crazy!

I recently finished Leonardo da Vinci by Walter Isaacson. I’ve long been intrigued by Leonardo and his seemingly limitless curiosity. I think I decided to finally pick up this book due to the release of another Isaacson biography that I don’t really have a desire to read — Elon Musk (cue booing sounds).

While I appreciated learning about Leonardo’s various endeavors and various aspects of his personal life, I found myself distracted by Isaacson’s narrative style. Maybe I’ve read too many of his books as of late (Benjamin Franklin, Einstein, Steve Jobs, Innovators, and Code Breaker), but I’ve found that his method of telling a biography has become somewhat repetitive.

That said, the book isn’t without its merits. The accounts of Leonardo’s projects, especially insights into various works such as his anatomical studies, the Last Supper and the Mona Lisa held my attention. These serve as reminders of da Vinci’s unique contributions to both art and science.

For those unfamiliar with Isaacson’s previous works, this biography might come off as more enlightening. But as someone who’s journeyed through his other books, there was a sense of “been there, read that.”

Overall, “Leonardo da Vinci” earns a 3 out of 5 from me. Informative, but perhaps not the standout biography of Leonardo I was hoping for.

The Making of the Atomic Bomb by Richard Rhodes captured my attention from start to finish. Going into it, I was fascinated by the idea of understanding the convergence of minds that led to the creation of one of history’s most powerful and controversial weapons. And of course, the recent buzz about the Oppenheimer movie contributed to this interest as well.

Rhodes doesn’t just delve into the technicalities of the bomb’s construction, which, on its own, would have been captivating. He masterfully presents the lives, backgrounds, and motivations of the characters involved.

A large part of the first third or so of the book digs into nuclear chemistry and the intense research going on to figure out these chain reactions. It was just absolutely fascinating.

What I found particularly interesting were the insights into the parallel efforts in Japan and Germany. It provided a unique view of the global race that was underway, further elevating the stakes and suspense of the story.

Throughout the book, there was this compelling juxtaposition: the brilliance of the minds at work against the backdrop of the impending devastation their creation would bring. It’s a testament to Rhodes’s storytelling that he managed to weave these narratives seamlessly.

“The Making of the Atomic Bomb” was a stellar read, and it easily gets a 5 out of 5 from me. For anyone curious about the people and the drama behind the science, this is a must-read.

Alrighty, I updated the logic this weekend and have Mr. RossBot operating on the hairy elephant website (Mastodon). (It’s also posting on Threads, if you’re into that sort of thing.)

I also updated the image model to use Stability.ai’s swanky new SDXL model. I’m pretty impressed with the results.

As much as technology improves our lives (and is integrated into literally everything we do), it really fucking sucks when the algorithm gets it wrong.

Earlier this summer, I posted a shop vac for sale, as I’ve done a number of times before (err, posting things for sale, not specifically shop vacs).

Soon after, I was banned for “violating community standards.” I have literally no idea what happened. But! Apparently you could appeal the decision if you felt it was incorrect.

So I did.

And was rejected.

So I appealed again.

And was rejected.

I appealed again. And now it looks like I am permanently banned from Facebook Marketplace. And there’s no way to appeal the decision. No way to contact customer support. Cool.

Anyway, here’s an image of Mark Zuckerberg wearing clown makeup, created using Stable Diffusion.

Alright, this is pretty awesome! 🎉

Last night at 11:27PM, my little generative AI side project, ArtBot, crossed 10,000,000 images created. People have created some pretty cool stuff.

Some random stats from Google Analytics since it launched on October 9th, 2022 to now:

• 71,000 unique users
• 8.3 million page views.