These are the type of persons who would get a girlfriend without a master degree in psychology.

It started as curiosity. I wanted to see if I could express business logic as simple choices and let the numbers fall out on their own.

The app is built interactively in Streamlit. I do not sit down with a spec or a backlog. I add one small idea at a time, refresh the page, react to what looks wrong, then adjust. It feels closer to sketching than programming. The interface tells me what the logic should be next.

Underneath there is a growing pile of rules about the business I am in.

I do not write code in the traditional sense.

I have never coded before and are solving my own problem done by one, this sure feels like magic!!

A Strong lifts 5x5 program build around squat, deadlifts, bench and shoulder press can always make me feel pumped for the day!

Also, I Spain your view of Spain is tainted. I think very few people would choose an average city in Spain over e.g. Copenhagen where 20% of the Danish population live.

I recently finished writing a book (in English), and I would like to turn it into a free eBook. I am Dutch and not particularly fond of my recorded voice, so I am experimenting with three audio formats—all using AI: 1. My voice cloned with AI: I will record a sample, then let the AI generate the full narration in my voice. 2. Standard AI narration: A clear, neutral voice that reads the book word-for-word like a traditional audiobook. 3. Podcast-style version: Using AI to rewrite and narrate the material in a more conversational and digestible format, like a podcast episode.

Curious to hear if anyone has done something similar, and open to recommendations on tools/platforms for any of the above.

Pleased to hear, thank you.

Comments URL: https://news.ycombinator.com/item?id=43866922

Points: 1

# Comments: 2

I fully agree with your point about the noise in this space, this is what we are trying to cut through :-).

A lot of what is marketed as “AI inspiration” is little more than buzzwords and recycled content. Your suggestion of a curated, immersive off-site experience, with hands-on workshops, industry-specific examples, and a structured learn-and-build format, is genuinely compelling. The idea of starting with interviews to assess skill levels and tailoring the programme accordingly is especially relevant for us.

If you know anyone who delivers this kind of applied AI learning in a serious and thoughtful way, I would very much appreciate an introduction.

Thanks again for the honest feedback.

There is also other elements: it sounds fun, offer great inspiration, support collaboration across teams, and help build a shared language around digital opportunities in the company.

Could we go to XYZ place in England, yes. Will it create the same magic, I doubt it.

Please note it is the Cowners idea, so he is willing to spend money on this out of his own pocket.

The idea was to expose a cross-functional group to the epicentre of innovation – to learn how leading tech companies actually use AI commercially, and bring back insights we could action.

The price tag? USD 500,000 for a week-long program for 10 people. That included visits, some programming, and facilitation. Unsurprisingly, we decided not to go ahead – but the desire to learn at the source is still very much alive. Our idea of a reasonable price tag is around USD 150,000 (where we recon half will go to flights and hotels).

So I turn to the Hacker News community:

1. Is it possible to arrange meaningful company visits to places like Google, OpenAI, or Anthropic without going through a costly middleman? How accessible are these companies for learning-focused groups?

2. Are top-tier universities like Stanford or Berkeley open to group visits, guest lectures, or curated AI sessions for international teams?

3. Are there local Bay Area companies or freelancers that help organise high-impact, cost-effective tech immersion trips?

4. Have you done this kind of trip before — what worked, what flopped, and what should we absolutely not miss if we self-organise?

Any advice, contacts, or shared experiences are welcome.

Thanks!

Comments URL: https://news.ycombinator.com/item?id=43771116

Points: 2

# Comments: 7

In short: It is not good enough. When it is good enough, customers adopt it.

1. different maturities 2. 24 different regions 3. Four different pricing categories

So the complexity of assigning the right input value to the right pricing curve is quite high.

However, a hybrid approach could perhaps be the way to go: I.e. monitor everyone’s chats and then scrape what looks like pricing info, which a human then translates into prices.

Is it realistic to expect this to be fully automated anyway?

In order to increase the quality of the market prices I therefore need to engage a global broker within my industry to get them to update prices globally, which would make my software not only the best in the world, but build a moat around the idea as no one can make something much better.

There are two problems: 1. What do I offer the partner in return? 1. Answer: equity, money, exposure, etc. I am not so bothered about reaching an agreement with the c suite of the company as the idea is good and relatively risk free for them. Also, management love big data project and “digitalization”. 2. This is a very manual process, so the 50-100-200 employees of my partner would need to daily go into a dashboard and plug in 10 numbers each. Not a huge effort, but I have a hard time seeing what could incentivize them, after all they are paid on comission they make and not inputs. This is where I feel it would fall flat, as no inputs make the software less valuable - the whole idea is to sell “live” prices anywhere in the world.

How would you guys think about such a problem?

Comments URL: https://news.ycombinator.com/item?id=38769570

Points: 1

# Comments: 7

Do you know of any FAISS / open source / one-click install wI have around 500 documents I want to be able to search in.

I have around 1000 research papers saved over the years that I would like to be able to search in, in a smarter manner than using CTRL+F. This is a personal tool for me to use doing work, and will not be shared with anyone else. It will run on my PC with 4 ghz cpu, 32 gb ram and 8 gb vram/gpu. Nvidia gpu.

I tried Pautobot but it is somewhat slow, which probably has something to do with my hardware. I also tried GPT4all but I couldn’t quite understand how I could train it on my data.

Basically I am looking for a search feature that can rank and return the best matches/paragraphs from these articles. I think vector searching sounds like the better option, but I have trouble finding an easy solution that involves vectorizing PDFs and then being able to search in them documents.

Pleased to hear your inputs

Note: I cannot write code.

Link: https://github.com/nrl-ai/pautobot/

Comments URL: https://news.ycombinator.com/item?id=36634459

Points: 2

# Comments: 0