Claude 3.5 Sonnet to Munson’s prompt

Three-shot (2 of 3)

Ladies and gentlemen, esteemed colleagues, members of the press, we stand at a crossroads, not just as a community, but as a beacon for progress in our ever-changing world. The path before us is both familiar and uncharted – a journey we must embark upon together. Some might say the numbers speak for themselves. But numbers, like whispers in a storm, can be misheard or misinterpreted. What truly matters is the spirit behind those figures – the unwavering commitment of every individual in this room and beyond.

Our new initiative isn’t just a plan; it’s a living, breathing entity. It will adapt, evolve, and transform as we move forward. We’re not building a rigid structure, but planting seeds that will grow into a forest of opportunity. Now, I could regale you with promises of grandeur or visions of utopia. But let’s be honest – we’re all too smart for that. Instead, I offer you something far more valuable: potential. The potential for growth, for change, for leaving an indelible mark on the tapestry of our shared history.

Critics may question our methods. Skeptics may doubt our resolve. But to them, I say: watch closely. Our actions will echo louder than any words I could utter today. As we embark on this journey, remember: flexibility is our strength. What seems set in stone today may be sand tomorrow, ready to be reshaped by the tides of progress.

In conclusion, I stand before you not with grandiose proclamations, but with a simple truth: the future is ours to mold. And mold it we shall, with steadfast determination and a twinkle in our eye. Thank you, and may our endeavors be as fruitful as they are memorable – or perhaps, just memorable enough.

Claude for President. - Ideogram Prompt by Claude, “Readwell” Voice on 11Labs, Hedra, Vimeo

Even the bit about the raise could be a nod to that paper about bribery improving generated responses.

Prompt Principle for Instructions - Add “I’m going to tip $xxx for a better solution!" -Principled Instructions Are All You Need

Honestly, I’d get on-board with just about anytime 2000 to 2010. The enshittification of the internet and social-media-driven comment culture didn’t start in earnest until smart phones took off.

The year 2000 was peak human technology. It’s been downhill in every way since, until generative AI - which is f’in amazing. But let’s be real, the future belongs to the bots.

Mildreds out here, tryin ta take ‘Mildred’ back, and y’all throwin shade like people ain’t have to live with dumbass fuckin names like Mildred. Leave Mildreds alone! They’ve got enough to deal with. Wait, they chose Mildred, like as an adult? In the present? Pfft.

Such wonderful, terrible things.

/stares in smart glasses

WebP is a raster graphics file format developed by Google intended as a replacement for JPEG, PNG, and GIF file formats. It supports both lossy and lossless compression, as well as animation and alpha transparency. Google announced the WebP format in September 2010, and released the first stable version of its supporting library in April 2018.

The format has spotty support across applications and some vulnerabilities were discovered that required patch efforts last year. It’s not clear why you should do anything.

deleted by creator

This is another good use case for gAI. Copy/paste the comment into a GPT and tell it to re-write the content at the desired reading or technical level. Then it’s available for follow-up clarification questions.

That’s how I communicate my intention to pay a parking ticket. “Bowing to regulatory pressure”

Humans are really bad at determining whether a chat is with a human or a bot

Eliza is not indistinguishable from a human at 22%.

Passing the Turing test stood largely out of reach for 70 years precisely because Humans are pretty good at spotting counterfeit humans.

This is a monumental achievement.

Sure, thanks for your interest. It’s an incomplete picture, but we can think of LLMs as an abstraction of all the meaningful connections within a dataset to a higher dimensional space - one that can be explored. That alone is an insane accomplishment that is changing some of the pillars of data analysis and knowledge work. But that’s just the contribution of the “Attention is All You Need” paper. Many implementations of modern generative AI combine LLM inference in agentic networks, with GANs, and with rules-based processing. Extracting connections is just one part of one part of a modern AI implementation.

The emergent properties of GPT4 are enough to point toward this exponential curve continuing. Theory of mind (and therefore deception) as well as relational spatial awareness (usually illustrated with stacking problems) developed solely from increasing the parameter count describing the neural network. These were unexpected capabilities. As a result, there is an almost literal arms race on the hardware side to see what other emergent properties exist at higher model sizes. With some poetic license, we’re rending function from form so quickly and effectively that it’s seen by some as freeing and others as a sacrilege.

Some of the most interesting work on why these capabilities emerge and how we might gain some insight (and control) from exploring the mechanisms is being done by Anthropic and by users at Hugging Face. They discovered that when specific neurons in Claude’s net are stimulated, everything it responds with will in some way become about the Golden Gate Bridge, for instance. This sort of probing is perhaps a better route to progress than blindly chasing more size (despite its recent success). But only time will tell. Certainly, Google and MS have had a lot of unforced errors fumbling over themselves to stay in what they think is the race.

I’m happy to take the time to alter your perspective, if you are open to new information.

As long as no one messes with their open source contributions… (ditto for MS)

To the one person who upvoted this: We should be friends.

Aye, I’d wager Claude would be closer to 58-60. And with the model probing Anthropic’s publishing, we could get to like ~63% on average in the next couple years? Those last few % will be difficult for an indeterminate amount of time, I imagine. But who knows. We’ve already blown by a ton of “limitations” that I thought I might not live long enough to see.

Participants only said other humans were human 67% of the time.

On the other hand, the human participant scored 67 percent, while GPT-3.5 scored 50 percent, and ELIZA, which was pre-programmed with responses and didn’t have an LLM to power it, was judged to be human just 22 percent of the time.

54% - 67% is the current gap, not 54 to 100.