ChatGPT

I just got usage capped on GPT-4 after 20 messages -- when I clicked "Learn More" on the message, I saw:

Thanks for your interest in GPT-4!

To give every Plus user a chance to try the model, we’re currently dynamically adjusting usage caps for GPT-4 as we learn more about demand and system performance.

We're also actively exploring ways for ChatGPT Plus subscribers to use GPT-4 in a less constrained manner; this may be in the form of a new subscription level for higher-level GPT-4 usage, or something else.

Please fill out this form if you'd like to stay posted.

Now admittedly I paste massive chunks of code into GPT-4 as part of my daily workflow and it's understandable if they're wanting to make the amount users get match with the price they're paying... but I was still a little taken aback by the customer-facing bullshit of that whole "To give every Plus user a chance to try the model" and "as we learn more". Like bro if you feel like setting a limit based on use then just tell me what the limit is and how I can get more if I need it.

Anyone else run into this? Anyone have a good alternative (besides just sending it all to the platform API and paying out the ass)? GPT-4 is actually capable with code in my experience in a way that 3.5 and Copilot are not.

I’ve updated @[email protected] to remember the whole tree of comments when replying to you, so it can do follow-up responses. You still have to mention it on every message, though. Example in the comments.

In this video, we recount an incident that occurred at OpenAI while researchers were trying to finetune GPT-2 to be as helpful and ethical as possible. It's narrated that inadvertently flipping a single minus sign led GPT-2 to become the embodiment of a well-known cardinal sin.

"presumably love" is so aggressively neutral it sounds a bit insulting

Earlier this week I discussed an example of ChatGPT giving 'placeholder' answers in lieu of real answers. Below is an example of what that looks like. I could swear this didn't used to happen, but it basically just 'doesn't' answer your question. I'm interested how often other people see this behavior.

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: @[email protected]. You can just mention it in a comment and it should reply. You can even mention both @[email protected] and @[email protected] 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;