Lienetic

How's it like working with schools/universities as a startup? I've always heard edtech can be a slow, bureaucratic sales cycle (and maybe not a high willingness to pay?).

I know a few different companies who ultimately moved out of the education market completely or just try to leverage their education traction as a beachhead to other markets. It sounds like you're focused on the education market - what's your take?

Can you explain a bit more about this? Are you building a profile of what I write and who I write it to? Fetching relevant examples and passing that through some (cloud?) LLM when writing the email?

I'm definitely curious on the technicals but there is also a bit of a trust element here - both on trusting that my email (likely some of my most sensitive data) is handled with care and trust that the actual responses are phrased well.

How are you handling the formatting and tone part of the email so that it doesn't sound like AI? I've tried to use AI tools for email multiple times but always end up significantly editing or rewriting the email myself.

Very cool, congrats on the launch! What's your plan for when one of the larger players like ElevenLabs or Google adds support for these languages? I would guess the reason why they haven't is because they don't see a large opportunity. How are you thinking about it?

This is really interesting, definitely going to give it a try! Seems fun but are you seeing people actually needing to make lots of videos like this? What's your vision - how does this become really big?

I'm curious - do you feel differently about some of these coding and coding-adjacent tools out there like Cursor and Lovable?

I know it's not unbiased, hence the quotes and why it is stated more as an observation of the how it can be difficult to find. Like most tools, this has flaws but I find it still useful because it presents questions to reflect on e.g. potential contradictions in logic and reasoning. I don't know of another way to get an analysis of inner thoughts easily.

Love the idea! It's hard to get an "unbiased" outside perspective, especially on more personal, inner thoughts. Will definitely try this out, thanks for sharing.

great response and one I wish people also abided by in normal day-to-day discussion. thank you, dang, for the great environment you maintain on HN.

Why do you think Anthropic has such a large system prompt then? Do you have any data or citable experience suggesting that the prompting isn't that important? Genuinely curious as we are debating at my workplace on how much investment into prompt engineering is worth it so any additional data points would be super helpful.

After this experience, do you think you'll ever build anything in the future with Electron? When do you think Electron is actually the right choice (if at all)?

Can anyone share some examples they think are strategic tools? I've read a solid number of these and am genuinely interested.

I was confused by this as ChatGPT launched in Nov 2022 and had tens of millions of users by end of 2022.

And though when we started our business in 2023 (ChatGPT wasn’t out yet), you could begin to feel that something like that was possible in a way it wasn’t before.

perhaps a typo in year?

I have not listened to him - can you explain a bit for the uninformed among us?

Can you explain further how you've come to the conclusion that "in the vast majority of cases there are objectively good and bad policies?"

Agreed. Is there a good tool you'd recommend for this?

Can we see the detailed CoT prompt?

I'd love to see that list!

Are there any approaches today that you've found are at least mostly reliable? Bonus points if it is somewhat clear/easy/predictable to know when it isn't or won't be.

We use human evaluation but that is naturally far from scalable, which has especially been a problem when working on more complicated workflows/chains where changes can have a cascading effect. I've been encouraging a lot of dev experimentation on my team but would like to get a more consistent eval approach so we can evaluate and discuss changes with more grounded results. If all of these metrics are low confidence, they become counterproductive since people easily fall into the trap of optimizing the metric.

Where can I learn more detail about the metrics you support and how they work?

I tried multiple other solutions but kept running into the problem that occasionally the framework would give me some score/evaluation of an LLM response that didn't make any sense, and there was minimal information about how it came up with the score. Often, I'd end up digging into the implementation of the framework to find the underlying evaluation prompt or classifier only to realize that the metric name is confusing or results are low confidence. I'm more cautious about using these tools now and look more deeply at how they work so that I can assess grading quality before relying on them to identify problematic outputs (e.g. hallucinations).

I assume you didn't mean to share a localhost link :)

Repo link from video description: https://github.com/kolbytn/mindcraft

Top-level JSON files seem to include all the prompts.

Cool concept! How was your process building and iterating on these prompts?

Out of curiosity, was this comment generated by an LLM (at least partially)?

The wording gives that kind of feel and now I'm wondering if my feeling around it is at all accurate.

Super cool, I'd love to learn more about your tech stack and how you capture data from my computer and phone! Screenshots and OCR like Rewind? I have a good number of lawyer friends who might be interested in this.

Musk says he canceled the show because it was too much like CNN. He didn’t comment on the interview questions.

...

"Like any enterprise, we reserve the right to make decisions about our business partnerships,” according to the post, which said that The Don Lemon Show is still “welcome to publish its content” on X.

This is compelling; the lag and crashes are the reason I am looking to self host anyways.

What specs are your machine? I'm trying to figure out what I can get that would be sufficient enough to switch off.

I do actually have an old computer that I use as basic home server but it can't support meaningfully heavy loads. For a Palworld dedicated server, I'd need something with 4 cores and 16gb which seems to cost ~$500 (e.g. for a NUC).

In comparison, all of these game server hosting sites charge ~$20/month, notably cheaper than that or hosting with any cloud host.

They also "manage it for you" which for us technical people is probably more of a con than a pro but honestly is fine for a game server as long as it works and allows reasonable access (most seem to at least let you FTP in).

I'm open to a better alternative if you have any suggestions

For the uninitiated among us - can you share more context on the research standards and the reasoning behind it? I'm interested and would like this to influence some decisions I have but would like to understand the confidence here :).

Do you have any personal recommendations on a good/affordable cloud host for this?

I briefly looked into how much it'd cost to run on an EC2 instance and it seems like it'd be order of $100 - $200 per month while these dedicated game server companies seem to be offering it, fully managed, for only $20/mo! I'm guessing they do this by having larger instances running many people's servers?

I'd prefer to manage and run this myself but when the price is an order of magnitude more to do so, it doesn't seem worth it to self host unless you happen to have a suitable always on home server sitting around.

This is so interesting! Are all these people asking you "can I..." questions just people you work with day-to-day and you've become their "go-to guy for smart stuff?"

Do you find it a pain to have to manage all of this for people?