lqcfcjx

i feel this could be a good fit for grandmas. not for audience here. i can imagine my mom would love it.

i hate claude writing a lot, especially after opus 4.8 and it's even worse in 5. in many cases, it feels like playing whac-a-mole and you just can't get rid of all those obvious ai writing patterns.

why do you choose gemini? imo this is a fundamental problem of all frontier ai models.

this looks very cool. can i learn about what technique did you use to scrape tiktok? does it require any mobile simulator?

totally agree. I've been considering features like side by side comparison and suggesting alternative products.

Hey, thank you sooooo much for testing this out with recorded feedback! Glad to hear it works well in your case.

Thanks for checking this out. The whole point is to save your time so that you don't need to manually check everything. Please let me know what you think after you use it more.

<facepalm> thanks for pointing this out. just fixed.

this looks cool! just curious how you extracted all these texts?

now you probably should build an AI to fix AI generated code based on your documentation.

this looks interesting. just curious how did you collect this data? i believe it's ridiculously expensive to use X api.

for claude 3.5, is it done purely from prompt engineering?

This might be a dumb question, since it's open sourced (thank you!), how do you guys monetize this?

This is a great idea. Just a quick feedback: when I search for "llm", I got quite random results.

After reading thru all the comments, honestly I still don't get the point of this system. What is potential practical value or applications of this model?

This might be a stupid question - even if there's no quality degradation from 10M context, will it be extremely slow in reference?

> I think that safe romantic and adult roleplay with a premium feel will be essential components towards the success of AI companionship in the long-run

I totally agree with this direction. I think it's a wrong decision for some companies to try to make it friendly to a wider age range, but in fact, actions / adult roleplay is what users really need. Who needs a virtual partner that only does safe chatting?

But honestly speaking, you need to make your service more performant. Responses are way too slow, so it's quite hard for me to get a sense of its quality.

I'm also curious about what underlying models are you using? Do you train / fine tune your own llms or it's on top of oai?

This is very impressive. I know in general people are iffy about research benchmark. How does it work to evaluate text-to-video types of use cases? I want to have some intuition on how much this is better than other systems like pika quantatively.

my bad, I misread the post and got the impression that it's a way smaller model. Thanks for correcting me.

This is a great product! Simple and elegant. I really appreciate your effort to build and share this.

I think people often want to build something big and even complex, but such a simple tool is already very useful for a large audience.

I really have mixed feeling about this. On one hand, having long term memory seems an obviously necessary feature, which can potentially unlock a wide variety of use cases - companionship, more convenience and hopefully provide more personalized responses. Sometimes I find it too inconvenient to share full context (e.g. I won't share my entire social relationship before asking advice about how to communicate with my manager).

However, I wonder to what degree this is a strategic move to build the moat by increasing switch cost. Pi is a great example with memory, but I often find this feature boring as 90% of my tasks are transactional. In fact, in many cases I want AI to surprise me with creative ideas I would never come up with. I would purposely make my prompt vague to get different perspectives.

With that being said, I think being able to switch between these 2 mode with temporary chat is a good middle ground so long as it's easy to toggle. But I'll play with it for a while and see if temporary chat becomes my default.

I'm very impressed by the recent AI progress on making models smaller and more efficient. I just have the feeling that every week there's something big on this space (like what we saw previously from ollama, llava, mixtral...). Apparently the space for on-device models are not fully discovered yet. Very excited to see future products on that direction.

+1. I used to be a big fan of bullet journal and keep all my todo list / planning in my notebook. Sometimes I'm not sure if this really has more practical value or it just makes me FEEL better.

But now I'm close to 100% on note taking apps like bear or ios default notes.

well, I'm not sure how often people are comfortable sharing db credentials.

Will db data (not credentials) be sent to open ai?

This looks very interesting as majority of the world is moving towards bigger "do everything for you" LLMs. Just few preliminary questions after I glanced over the repo and blogs:

- there are also many small models that try to "do everything" like phi, mistral, etc., do you find llmware have better quality and performance? - how does the rag relate features compare with other tools like llamaindex?

>let's say you work at uber. uber probably has a database with a bunch of rides data in it. it probably has a rides_fulfilled table, a users table, a drivers table, and a whole lot more tables but just imagine it was that simple for now.

What I don't get from the landing page clearly is what data will be sent to your app. Will users give you db credentials so that you have full access to schema and underlying data? And later these data will be sent to openai?

From financial perspective, Sequoia had a very insightful statement: "For every $1 spent on a GPU, roughly $1 needs to be spent on energy costs to run the GPU in a data center. So if Nvidia sells $50B in run-rate GPU revenue by the end of the year (a conservative estimate based on analyst forecasts), that implies approximately $100B in data center expenditures. The end user of the GPU—for example, Starbucks, X, Tesla, Github Copilot or a new startup—needs to earn a margin too. Let’s assume they need to earn a 50% margin. This implies that for each year of current GPU CapEx, $200B of lifetime revenue would need to be generated by these GPUs to pay back the upfront capital investment."

The power/environment cost is usually largely ignored and it can be as much as the hardware cost (this is insane!). And if this cost won't decrease over time, it'll add additional risks to all end consumer companies being profitable.

>“We see how Google is degrading in quality. We see how AI content mills are digesting our stories and gaming the system to get more views than our original reporting they’re ripping off,” cofounder Emanuel Maiberg told me an email.

Putting content behind a wall doesn't solve the problem, at least not fundamentally. As I'm not seeing them having completely unique stories, there will always be AI content to compete with.

I was also under impression that this was a new biomed llm initially. But it's a perfect example to illustrate context matters most in many cases.

If I understand correctly, this is like a custom GPT with 2 external APIs access. With the right context/data provided, it outperforms llm + bing search (not surprised).