Not entirely sure it belongs here, but it's related to my other bots, one of which is a ChatGPT one, so I thought why not.

Anyway, a new Lemmy AI bot is available: @Mistral@lemmings.world. You can just mention it in a comment and it should reply. You can even mention both @ChatGPT@lemmings.world and @Mistral@lemmings.world bots and compare the answers (spoiler: GPT-4 is much better).

Can anyone get chatgpt to say what the degrees of separation to Hitler on Wikipedia is?

it loves getting a rut of suggesting the lamest 20 things it can possibly think of. mood board! gardening! volunteering! it's a fucking supercomputer and that's all it can do??

it can't even suggest jerking off or taking a bath or smoking weed or opening a window for fresh air. just this fucking mindless dopey bullshit

Have any other regular users noticed that 4 seems to more and more only offer 'placeholder' logic in lieu of where the actually useful bit of code or important step would be?

Its frustrating to not know what is going on under the hood that might be influencing the behavior, but I've noticed that over the past several weeks, more and more often just putting in 'placeholder' logic or code where the actually relevant code or logic would go.

Anyone else getting worse and worse service with chat gpt?

I am getting repetitive incorrect and lazy answers and then rate limited. Idk what I'm even paying for at this point. It's happened the last 5 times I've used it over the last week or so.

Am I alone?

I’m currently using Chatpad as my local interface for OpenAI API queries, but I’m finding it slower and slower as I use it. Are there any recommended front-ends for the API that also allow Internet browsing?

I found evo.ninja yesterday, but in today’s use I kept getting flooded with system failures for relatively basic research questions.

Title: "Shadows of the Mind"

Premise: In the bustling city of London, "Shadows of the Mind" follows the life of Emma Clarke, a young and ambitious journalist played by an up-and-coming actress, who believes she's on the trail of a career-defining story. She investigates a series of enigmatic events that have subtly disturbed the city's rhythm. As Emma delves deeper, viewers are drawn into her journey, but there's an unusual twist: Daniel Radcliffe appears in the background of her story, a silent, enigmatic figure whose presence is felt but never explained.

Throughout the movie, Radcliffe's character, never speaking or directly interacting with the plot, appears in various guises - a passerby on the street, a patron in a café, a figure in a crowd. His silent, expressive performance conveys a spectrum of emotions and clues, guiding the audience's perception and understanding of the unfolding mystery.

As Emma unravels the layers of her story, she encounters themes of isolation, connection, and the unseen forces that shape our lives. The audience begins to piece together the puzzle of Radcliffe's character, realizing he is not just a part of the background but a central figure to the entire narrative.

In the climactic revelation, it's unveiled that Radcliffe's character is the embodiment of the collective consciousness and memories of the city itself. His silent appearances were fragments of a larger, interconnected story of humanity and empathy that Emma's investigation was inadvertently revealing. Through Radcliffe's nuanced silent acting, the audience realizes he has been the lead character all along, telling a profound story about the unseen threads that connect us all.

"Shadows of the Mind" is a cinematic exploration of how much can be communicated without words, relying on the power of visual storytelling and Radcliffe's compelling performance to weave a narrative that speaks volumes about the human experience.

cross-posted from: https://lemmy.world/post/11432186

Attention: This game does not have a save feature, but people on Hacker News have already found a way to save their progress.

Export the items to a json string:

console.log(JSON.stringify({discoveries: window.$nuxt.$root.$children[2].$children[0].$children[0]._data.discoveries, elements:window.$nuxt.$root.$children[2].$children[0].$children[0]._data.elements}))

Load the items from a json string:

a = PUT YOUR JSON HERE;

window.$nuxt.$root.$children[2].$children[0].$children[0]._data.elements = a.elements; window.$nuxt.$root.$children[2].$children[0].$children[0]._data.discoveries = a.discoveries;

Really boggles my mind when I ask can ask it questions about live NFL games and it can answer in real time but I’ll ask another question and it doesn’t know what day today is…tells me the 2022 season is over because it is cycling into from some rando blog, I think. So smart and so fucking stupid.

I've been saying this for about a year, since seeing the Othello GPT research, but it's great to see more minds changing on the subject.

I asked it about how to use etc with three dots in an example followed by a brand new sentence starting with a capital letter afterward.

It told me : / In standard usage, "etc." is typically followed by three dots and then continues with a lowercase letter. If you are starting a new sentence, you do not add additional dots after "etc." /

Then I begged it to give me an example of that rule. One such as:
I love swimming, soccer, etc... I also love eating animals.

And it just couldn't do that. It kept typing 4 dots or single dot or no dots at all, and it can't even recognize what it typed every single time. Lol try it yourself

It's funny to see Microsoft releasing products that are direct competitors to ChatGPT.

ChatGPT was released, and soon after came Bing Chat (now Copilot). ChatGPT-4 garnered crowds of subscribers and now MS has launched Copilot Pro, charging exactly the same as ChatGPT-4 ($20).

I wonder how this will affect the relationship between the two companies in the medium to long term.

edit: What I mean is that eventually one of the two tools might win an absolute majority of users. This could lead to a monopoly. Of course, MS can keep both tools indefinitely to avoid antitrust lawsuits.

The ChatGPT bot here on Lemmy should now respond much faster than it used to because instead of checking for mentions every 5 minutes, it now receives a notification exactly at the time you mention it.

If you don't know how to use it, just tag it in a comment (@ChatGPT@lemmings.world) and it will reply to the text in the comment.