rollinDyno

I understand the sensation of disgust when being offered to read a piece of AI slop. However, I'm actually curious about how our sensitivity towards slop will evolve. I imagine people will have varying degrees of tolerance.

Afterall, AI slop doesn't necessarily mean the prompter didn't read. It just means they're OK with the AI phrasing. It's also possible that they read the output and had the AI update with whatever edits they prompted.

Writing this comment makes me more convinced that if us users of AI want our written work to be taken seriously, then we should also share our prompts. I hope we quickly converge into a standard way of sharing the prompts that generated a given product.

This is just Moscow

Can we make it have access to the "Now Playing" MacOS feature that plays/pauses whatever I'm listening to? It could be a Youtube video, a track on Spotify or a video on VLC.

I read the accuracy report and I'm yet to find on what basis is your accuracy score being built on. Is it the number of personas that re-post, like, comment, see, all of the above?

I think you guys might be onto something but I'm still skeptic as to whether you are the most accurate (on whatever metric). It's not surprising that you beat a survey of experts, or straight out of the box commercial LLMs.

I'm more interested in seeing how your model performs against purpose specific models that are currently industry standard. Unless you're making the claim that you're the first service to predict content engagement?

Yea, let me send it your way once I have it! Please update your profile with contact info.

Sure, I'd love to have your feedback. Let me package this into my first beta and I'll reach out.

Nothing yet, but I can keep you posted. Please update your HN profile with contact info.

Thanks for sharing! Yes, I quickly came to that conclusion as well. It's put me in the novel position whereby product development is about finding the right prompt, and maybe even about finetuning.

It's pretty much the same, but I have a few ideas to make my app stand out. Thanks for sharing! Nice to see the idea has potential.

Have you ever wanted to write your life story but found it too overwhelming? I’m developing an app that acts as your personal interviewer, guiding you through your memories and helping you share them with your loved ones.

The app is designed for older adults who enjoy reminiscing but struggle to organize their thoughts into a coherent narrative. The goal is to preserve their hard-won insights and pass them down—to family members who may be too busy to ask the right questions now, and to future generations who would otherwise never hear these stories.

I have a working prototype that allows me to test the interview flow, and I’ll soon be sharing it with friends and family for initial feedback. I’m now looking for a designer to collaborate on the next phase.

Design will be a critical part of this app. The way stories are visually presented will be central to the user experience and will likely determine the app’s success. If you’re a designer interested in this kind of work, I’d love to hear from you. Given the text-heavy nature of the app, experience with typography and content-focused design will be especially valuable.

I'm sorry for your loss.

I'm interested but I'm not getting the confirmation email.

I recently finished my PhD studies in social sciences. Even though it did not lead me to career improvements as I initially expected, I am happy I had the opportunity to undertake an academic endeavor before LLMs became cheap and ubiquitous.

I bring up my studies because what the author is talking about strikes me as not having been ambitious enough in his thinking. If you prompt current LLMs with your idea and find the generated arguments and reasoning satisfactory, then you aren't really being rigorous or you're not having big enough ideas.

I say this confidently because my studies showed me not only the methods in finding and contrasting evidence around any given issue, but also how much more there is to learn about the universe. So, if you're being rigorous enough to look at implications of your theories, finding datapoints that speak to your conclusions and find that your question has been answered, then your idea is too small for what the state of knowledge is in 2025.

It's worth mentioning that defenders of Prevost in Peru are saying that those allegations were manufactured by his political enemies. Prevost was active in the fight against the Sodalitium, a catholic society with ample accusations of brainwashing and sexual abuse. This society was recently supressed by Bergoglio.

I'm not even interested in verifying if these claims are based on randomly controlled trials when their outcome variables are self-reported imagined impatience and predicted behavior! By now in 2025, psychology studies should be painfully self-aware of the lack of credibility in their instruments, guess not.

Everyone who has been working on RAG is aware of how important source control is. Simply directing your agent to fetch keyword matching documents will lead to inaccurate claims.

The reality is that for now it is not possible to leave the human out of research, so I think the best LLM can only help curate sources and synthesize them, but cannot reliably write sound conclusions.

Edit: this is something elicit.com recognized quite early. But even when I was using it, I was wishing I had more control over the space over which the tool was conducting search.

This is nice, quite expensive tho.

Government is already intervening, you think people are going at only 46 kmh because of goodwill?

In his essay, Eco says no instance of fascism will present itself with all items. He starts out by saying that fascism is very hard to define, so the 14 item list is meant to be a soft guide more than an absolute rule book.

I am starting to accept that this is a conversation we are going to be having over and over again, even after Elon and Trump. We are rightly traumatised by the excesses of the past, so it's very easy to imagine that any slight will inevitably lead to full on fascism.

This last qualification of fascism could be key, it differentiates 20th century fascism to what we are seeing today. We don't yet know whether this new form of fascism is just as harmful. For instance, when debating about whether Elon—who meets many of the elements in Eco's list—is a nazi or not, people are having very different conversations. There is no nazi party Elon can be a member of so that's not what I've been interested in. For me it has been more about the possibility of Elon advocating the same extreme policies fascist parties did. We could say he shares some of the worldview as the white supremacists, but would he go as far as implementing a 'final solution' to remedy the diagnosis?

Something I quickly learned while retooling this past week is that it’s preferable not to add opinionated frameworks to the project as they increase the size of the context the model should be aware of. This context will also not likely be available in the training data.

For example, rather than using Plasmo for its browser extension boilerplate and packaging utilities, I’ve chosen to ask the LLM to setup all of that for me as it won’t have any blindspots when tasked with debugging.

Why would it require a director if a generative process can use the information it has on audience (even individual) preferences to produce the story and format that will best hook consumers?

I think the other thread did a good job showing you that it's the other way around, people who have been in the industry do not tend to have the imagination people with fresh eyes (and maybe some tech chops) do.

An example I had in mind was when Affleck was speaking of being able to generate the show but with their preferred cast from a different production. He really has no clue that people will be generating themselves and their friends as the main characters of these stories. Like this one, there are many other examples where I thought he was lacking creativity.

Kudos to him for spending time thinking about it but I'm surprised how well received his thoughts have been for just stringing a few ideas together.

I'm not in the industry and I can tell he's failing to conceive many possibilities. I don't understand why he's being praised, I guess confidence impresses people.

This makes sense for the current add-on wave but expect the launch of independent AI platforms to increase in the coming year.

Keep in mind anyone can publish on Arxiv and it's not at the top of HN on the merit of its research contributions.

Hey at least you weren't one of those kids who ran into those online faucets that were giving bitcoins for free and didn't think too much about it.

That was not the impression I got from his Twitter. He might be able to build stuff but his ability to explain social phenomena is really poor (especially for someone with an economics degree).

Explain the irony.