Company website: https://ssi.inc

Has anyone else noticed this kind of thing? This is new for me:

povies.append({ 'tile': litte, 're': ore, 't_summary': put_summary, 'urll': til_url })

"povies" is an attempt at "movies", and "tile" and "litte" are both attempts at "title". And so on. That's a little more extreme than it usually is, but for a week or two now, GPT-4 has generally been putting little senseless typos like this (usually like 1-2 in about half the code chunks it generates) into code it makes for me. Has anyone else seen this? Any explanation / way to make it stop doing this?

cross-posted from: https://lemmy.dbzer0.com/post/21273521

For people who don't like much the new font on the ChatGPT website, which font would you rather prefer to use (Except Inter, Roboto, DM Sans)? I noticed that there are people who don't like the current font, so I decided to add a custom fonts for the web extension that already customizes the ChatGPT UI. It would be really helpful to know more specifically what would be more pleasant for your eyes to read.

PS. if someone is into customizing, the extension is GPThemes (There are Firefox's Desktop and Android versions too)

As the title says, I updated the bot a day or so ago, so you can chat with it in the comments. It should now also support context, meaning it knows the whole comment chain. And you don't have to tag it if you're replying to it.

It's so frustrating.

Even very basic things like "Summarize this video transcipt" on GPTs built specifically for that purpose.

Firstly, it cannot even read text files anymore. It straight up "cannot access documents". No idea why, sometimes it will act like it can, but it becomes obvious it's hallucinating or only read part of the document.

So ok, paste info in. GPT will start giving you a detailed summary, and then just skip over like 40 fucking percent of the middle, and resume summarizing at the end.

I mean honestly, I'm hardly asking it to do complex shit.

I have absolutely no idea what lead to this decline, but it's become so bad it is hardly even worth messing with it anymore. Such an absolute shame.

Chat GPT Gratuit Améliore l'Efficiacité Professionnelle

L'intégration de Chat GPT Gratuit dans votre routine professionnelle peut transformer radicalement votre gestion du temps et de la productivité. Cet outil d'IA, développé par OpenAI, est capable de prendre en charge une multitude de tâches automatisables, comme la rédaction de courriels, la planification de réunions ou la création de contenus textuels divers. Chat GPT Gratuit permet ainsi aux professionnels de se concentrer sur des activités à plus grande valeur ajoutée.

Accès Facilité à l'Information avec Chat GPT Gratuit

Chat GPT Gratuit est également un puissant moteur de recherche personnel qui répond instantanément à vos questions, qu'elles soient d'ordre général ou spécifique. L'outil utilise une base de données vaste et une compréhension contextuelle pour fournir des réponses précises et pertinentes, ce qui en fait un excellent support pour l'apprentissage et la prise de décision rapide.

Un Compagnon d'Apprentissage avec Chat GPT Gratuit

Pour les étudiants et les apprenants de tous âges, Chat GPT Gratuit se présente comme un assistant d'étude idéal. L'outil aide à expliquer des concepts complexes, offre des résumés de matériel étudié et peut même aider à la préparation d'examens ou de présentations. Sa capacité à adapter les réponses au niveau de compréhension de l'utilisateur en fait un soutien personnalisé efficace.

Interactions Multilingues Grâce à Chat GPT Gratuit

Avec la capacité de traiter et de répondre dans plusieurs langues, Chat GPT Gratuit est un outil inestimable pour briser les barrières linguistiques. Que ce soit pour traduire des documents ou pour communiquer avec des interlocuteurs étrangers, Chat GPT Gratuit facilite l'interaction sans effort, élargissant vos horizons personnels et professionnels.

Sécurité et Confidentialité avec Chat GPT Gratuit

La sécurité de vos données est une priorité pour Chat GPT Gratuit. L'outil est conçu pour garantir la confidentialité des échanges et la protection des informations personnelles. Les utilisateurs peuvent bénéficier de toutes les fonctionnalités de l'IA tout en ayant la certitude que leurs données sont sécurisées et traitées avec le plus haut niveau de respect des normes de confidentialité.

Conclusion: Pourquoi Chat GPT Gratuit est Essentiel dans Votre Vie Numérique

En adoptant Chat GPT Gratuit, vous optez pour une solution qui enrichit votre expérience numérique quotidienne. Cet outil polyvalent vous aide à naviguer dans vos tâches quotidiennes avec plus d'efficacité, d'accès à l'information et de facilité d'interaction, tout en restant sécurisé. Que vous soyez professionnel, étudiant ou simplement curieux de la technologie, Chat GPT Gratuit est un atout indispensable pour tirer le meilleur parti de l'intelligence artificielle.

Hello everyone, I recently discovered ChatPDF, and I'm very impressed with how it answers and performs.

source

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 @Mistral@lemmings.world 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: @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.