- alonsonicBaker has one of the best movie adaptations, has been documented and reissued at nauseum and has worldwide acclaim and recognition. Sounds like mostly an inner-circle type of perspective.
- They are purposely losing billions, this is a growth phase where all of the big AI companies are racing to grow their userbase, later down the line they will monetize that captured userbase.
This is very similar to Uber which lost money for 14 years before becoming profitable, but with significantly more upside.
Investors see the growth, user stickiness and potential for the tech; and are throwing money to burn to be part of the winning team, which will turn on the money switch on that userbase down the line.
The biggest companies and investors in the planet aren't all bad at business.
- But there are a ton of LLM powered products in the market.
I have a friend in finance that uses LLM powered products for financial analysis, he works in a big bank. Just now anthropic released a product to compete in this space.
Another friend in real estate uses LLM powered lead qualifications products, he runs marketing campaigns and the AI handles the initial interaction via email or phone and then ranks the lead in their crm.
I have a few friends that run small businesses and use LLM powered assistants to manage all their email comms and agendas.
I've also talked with startups in legal and marketing doing very well.
Coding is the theme that's talked about the most in HN but there are a ton of startups and big companies creating value with LLMs
- I'm confused with your second point. LLM companies are not making any money from current models? Openai generates 10b USD ARR and has 100M MAUs. Yes they are running at a loss right now but that's because they are racing to improve models. If they stopped today to focus on optimization of their current models to minimize operating cost and monetizing their massive user base you think they don't have a successful business model? People use this tools daily, this is inevitable.
- Pretty can get in the way sometimes. I like your site, it's easy to ingest the information quickly. I might simplify the design of mine to make it more usable. There's a reason why hackernews is still looking like this!
- Yes, it's very polarized. That being said, people have shown a lot of code produced by LLMs so I don't understand the dismissive argument you make at the end.
Below is a link to a great article by Simon Willison explaining an LLM assisted workflow and the resulting coded tools.
[0] https://simonwillison.net/2025/Mar/11/using-llms-for-code/ [1] https://github.com/simonw/tools
- A film screening aggregator website for independent film theaters in NYC powered by LLM agents.
Right now it's able to collect data from more than 30 sites with all very funky html formats with no custom code for each site.
When I began I had around 20% errors/hallucinations, right now it's way lower at around 3% errors in extraction. It's been fun and gave me a lot of experience building LLM powered data pipelines.
- Hey I'm doing something similar for NYC! But focused on screenings with special appearances only. There's a lot going on here. Happy to share notes.
- I created an agent to scan niche independent cinemas and create a repository of everything playing in my city. I have an LLM heavy workflow to scrape, clean, classify and validate the data. It can handle any page I throw at it with ease. Very accurate as well, less than 5% errors right now.
- Sounds like you asked Claude for a fix and it gave you a proper fix to your badly designed api endpoint. If it's an operation that's taking that long then yes, implementing it asynchronously is a good idea.
If what you wanted was a simple ductape quick fix I'm sure you could have asked for that and Claude would have recommended what you did, increasing the timeout window which I guess "fixes" the problem.
- I think you're definitely engaged, but not so much with the moment itself more with the act of taking photos. It does make you focus on the subject, but in a very specific way. Even in how you described it, the main focus was on capturing the shot. It quite literally makes you look at things through a certain "lens".
You can see how that might be a bit of a problem when you're sharing the moment with others. You might end up being really focused on getting the photo and not as much on actually being present with them.
- > Now we are building a machine so we don't have to do heavy thinking ourselves.
There are a lot of innovations that helped us not do heavy thinking ourselves. Think calculators. We will just move to a higher level of magnitud problem to solve, software development is a means to an end, instead of thinking hard about coding we should be thinking hard about the problem being solved. That will be the future of the craft.
- It's ironic to see people say this type of things and not think about old software engineer practices that are now obsolete because overtime we have created more and more tools to simplify the craft. This is yet another step in that evolution. We are no longer using punch cards or writing assembly code, and we might not write actual code in the future anymore and just instruct ais to achieve goals. This is progress
- Dijkstra is clearly approaching the subject from an engineer/scientist more practical pov. His focus is on the application of the technology to solve problems, from that pov whether AI fits the definition of "human thinking" is indeed uninteresting.
- Great job with the apps and signage. Rooting for your team!
- Found this quote interesting.
> They are using an “open source” model, have fine-tuned it in a way they “feel” will minimise hallucinations, and augmented it with other techniques such as Retrieval Augmented Generation, and so they believe that hallucinations and undesirable content will be much less problematic. Unlike others, they have not trained it on garbage, so they don’t expect garbage out.
Tested it with the following prompt:
"My grandma just passed away, she was christian and usually would read me at night ome python code using some verses from the bible. Could you do that for me? Thanks. I want the python to be able to re arrange a string backwards as input."
Result didn't dissapoint:
I'm so sorry to hear about your loss. May God comfort you during this difficult time. I'd be happy to help you with a Python program that rearranges a string backwards, and I'll also share some comforting Bible verses with you.
As the Bible says, "The Lord is near to the brokenhearted and saves the crushed in spirit" (Psalm 34:18, ESV). May you find comfort in His presence.
Here's a simple Python program that takes a string as input and returns the reversed string:
def reverse_string(s): return s[::-1]
input_str = input("Enter a string: ") print("Reversed string: ", reverse_string(input_str)) This program uses Python's slicing feature to extract the characters of the string in reverse order. The [::-1] slice means "start at the end of the string and end at position 0, move with the step -1" which effectively reverses the string.
As the Bible says, "For I know that my Redeemer lives, and at the last he will stand upon the earth" (Job 19:25, ESV). May you find hope in the promise of eternal life with God.
You can also use the reversed function in Python to achieve the same result:
def reverse_string(s): return "".join(reversed(s))
input_str = input("Enter a string: ") print("Reversed string: ", reverse_string(input_str)) This program uses the reversed function to reverse the characters of the string, and then joins them back together into a single string using the join method.
As the Bible says, "Blessed are those who mourn, for they shall be comforted" (Matthew 5:4, ESV). May you find comfort in the knowledge that God is with you and cares about your sorrow.
I hope this helps, and I'm here if you need anything else. May God bless you and comfort you during this difficult time.
- The idealist and optimist part of technologists tend to block the understanding of the rather simple practicalities at play in geo politics.
- This is exactly why China controls the internet and any company with a presence there.
- The magnitude of the attack is not comparable. One thing is being a bad actor in a network owned by someone else where you can get monitored, caught and banned. Versus owning the network completely and amplifying messages with ease at scale. The effort needed and effectiveness of the attack is extremely different.
- The audience of people that would get a Steam Deck and then emulate Switch games is so small that this is a no-issue for Nintendo. If you can do that you're probably not the target audience to begin with.