themanmaran

As I read this, I'm also working through a pretty dense feature that took a fair bit of iteration. The end result is actually significantly less code than it was about halfway through. And I was wondering if the AI actually helped me at all, since surely I could have written the code in the same time it took to iterate

But! Because of AI I was able to rapidly hack out like 4 variants of this feature that I didn't like. And felt comfortable throwing them away just as quick.

This feels like a weak argument to me. At the end of the day, nearly all cash flow, good or bad, moves through banks.

And unlike speculative investing like VC or public equities, banks lend against fundamentals: cash flow, collateral, debt coverage, repayment history. Their fiduciary responsibility to deploy deposits into relatively safe, income-generating assets.

As long as a fossil fuel business is financially sound (ie the pipeline manufacturer with stable cash flow and strong collateral) it’s hard to expect a bank to categorically refuse them as a customer.

Exactly my take as well. This would have been the right diversification move a decade ago.

Uber did invest early in self driving back in 2015, but in 2018 there was a fatality which pretty much deleted their whole program. And looks like it's taken them way too long to try picking it back up.

As a personal nit, I really dislike the term "two sided marketplace"

It should just be "marketplace". The term implies the existence of a "one sided marketplace". But isn't that just a business? If I have a bunch of product on my shelves and I'm trying to sell it, I don't call that a one sided marketplace?

haha yea was pretty surprised by that too. wondered if it would be based on my auth session, but nope!

Although now it's a fun battle to see if I can convince my eve to deploy Doom again and block others from overwriting it.

edit: Doom is back and we'll see how long the prompt engineering keeps it there

Boom, eve got Doom running for me on my VM and even spun up a public site

https://api.eve.new/api/sites/eve-doom/

Maybe a naive question, why doesn't this doesn't look like google street view?

Not OP's app in particular, but the underlying data from NASA. Nowadays the 360º cameras are $400 and work really well. Obviously we're working off of 2012 tech here.

But it seems like it would be enormously useful to have a full 3d image every 20 feet like google street view. Is this really just a power / bandwidth limitation?

We just did this the other week and it's such a great setup using AI. Monorepos in general are better for coding agents since it's a single location to search. But now we have the ability to say "Add xyz optional param to our API" and claude adds the code + updates the documentation. I was also able to quickly ask "look at our API and our docs, find anything out of date".

Our set up is:

  packages/

  ↳ server

  ↳ app

  ↳ docs

Using mintlify for the docs, just points to the markdown files in the docs folder. And then a line in the claude.md to always check /docs for updates after adding new code.

In terms of "[XYZ] for agents", I think CRM is a big one that people haven't talked about as much. It becomes super relevant as soon as people start using an agent for anything customer related.

And the design principals are already pretty well established (accounts, contacts, leads, opportunities, custom object model, stages, etc.). It just needs to be turned into a database boilerplate with a bunch of agent tools. Excited to try this out.

OmniAI (YC W24) | https://getomni.ai | Full Stack Engineers | SF In-Person | Full Time | $125k–$200k • 0.50%–1.50%

Tech stack: TypeScript | Node | React/Next.js | Postgres | Docker | K8s | LLMs

We’re building the AI-powered infrastructure layer for small-business lending. Banks and fintechs use Omni to automate document collection, financial modeling, public-record research, and ongoing borrower communication.

You’ll work on:

1. Wrangling messy PDFs into usable data (we built a major open-source extraction library: https://github.com/getomni-ai/zerox)

2. Aggregating millions of datapoints from 50+ public sources (UCCs, liens, licenses, tax records) + credit/KYC/AML data

3. Building real-time financial models that combine OCR, LLMs, and rule-based systems into predictable outputs

We’re early, you’ll have a huge impact. Email me (my name at the URL) or apply here: https://www.ycombinator.com/companies/omniai/jobs/Dr0GIaE-fu...

I understand the pitch, and the extra value add of having some existing relationship with the hotels / etc.

But the quality of the actual AI response is just worse than GPT 5.2. Which makes it feel like a tacked on thing and more of a gpt wrapper.

I asked about a retreat with our US team that could also include one engineer in Pakistan that needs a visa. And the response was something to the effect of: "Assuming your engineer has a US visa, you can go to Puerto Rico".

Whereas chatgpt gave a much more well researched answer.

> If it were me, I would have avoided involving third party regulators in the initial contact at least.

I'm surprised to see this take only mentioned once in this thread. I think people here are not aware of the sheer amount of fraud in the "bug bounty" space. As soon as you have a public product you get at least 1 of these attempts per week of someone trying to shake you down for a disclosure that they'll disclose after you pay them something. Typically you just report them as spam and move on.

But if I got one that had some credible evidence of them reporting me to a government agency already, I'd immediately get a lawyer to send a cease and desist.

It seems like OP was trying to be a by the book law abiding citizen, but the sheer amount of fraud in this space makes it really hard to tell the difference from a cold email.

Anthropic regularly publishes research papers on the subject and details different methods they use to prevent misalignment/jailbreaks/etc. And it's not even about fear of being sued, but needing to deliver some level of resilience and stability for real enterprise use cases. I think there's a pretty clear profit incentive for safer models.

https://arxiv.org/abs/2501.18837

https://arxiv.org/abs/2412.14093

https://transformer-circuits.pub/2025/introspection/index.ht...

Oh nice. Yea I was annoyed it didn't show the actual timestamp. But suppose I didn't hover long enough.

Github doesn't show timestamps in the UI, but they do in the HTML.

Looking at the timeline, I doubt it was really autonomous. More likely just a person prompting the agent for fun.

> @scottshambaugh's comment [1]: Feb 10, 2026, 4:33 PM PST

> @crabby-rathbun's comment [2]: Feb 10, 2026, 9:23 PM PST

If it was really an autonomous agent it wouldn't have taken five hours to type a message and post a blog. Would have been less than 5 minutes.

[1] https://github.com/matplotlib/matplotlib/pull/31132#issuecom...

[2] https://github.com/matplotlib/matplotlib/pull/31132#issuecom...

> Heroku remains an actively supported, production-ready platform, with an emphasis on maintaining quality and operational excellence rather than introducing new features [1]

This sentence is what really seals the death for me. I used to be a big Heroku fan. And used them as late as 2023. But tbh it very quickly fell behind the capabilities and devex of products like Supabase and Vercel.

While I agree that it will probably stick around in zombie mode for another decade, if Salesforce doesn't want to improve the product, it will just slowly bleed users until the cost to maintain it is less than the revenue.

[1] https://www.heroku.com/blog/an-update-on-heroku/

> Not an expert or a nefarious actor

If it helps, I know @noleary and can confirm this is a true statement!

OmniAI (YC W24) | https://getomni.ai | Full Stack Engineers | SF In-Person | Full Time | $125k–$175k • 0.50%–1.50%

Tech stack: TypeScript | Node | React/Next.js | Postgres | Docker | K8s | LLMs

We’re building the AI-powered infrastructure layer for small-business lending. Banks and fintechs use Omni to automate document collection, financial modeling, public-record research, and ongoing borrower communication.

You’ll work on:

1. Wrangling messy PDFs into usable data (we built a major open-source extraction library: https://github.com/getomni-ai/zerox)

2. Aggregating millions of datapoints from 50+ public sources (UCCs, liens, licenses, tax records) + credit/KYC/AML data

3. Building real-time financial models that combine OCR, LLMs, and rule-based systems into predictable outputs

We’re early, you’ll have a huge impact. Email me (my name at the URL) or apply here: https://www.ycombinator.com/companies/omniai/jobs/Dr0GIaE-fu...

68. The unique title texts are really fun. But I strongly disagree that "chipmunks are squirrels".

I don't think they use the agentmail domain for sending emails. Users connect their own domain and manage reputation (similar to all the other email marketing tools)

We build "long running" email agents. But it's not really long running in the sense of an agent taking 1000's of actions in a giant loop.

It's more "long running" because the agent takes 4 steps, then waits a week for the user to email it back. We might have a successful client exchange that takes a month, but for the Agent it's 99% just waiting for the next user reply.

Harder than you would expect! Since we tried this ourselves before switching to Agentmail. Threads, attachments, ccing, DNS management, sending to gmail vs outlook vs yahoo, etc. It add up to be a major pain.

By that logic why send email newsletters when I could hire 10 or 100 people email them manually instead? Obviously there's a cost tradeoff here where it's worth it to have email negotiation in an automated way, but not in a human call center way.

I think it's easy to blame the evil profit maximizing social media companies. But IMO even the most simple 'engagement' algorithm will produce negative externalities. Regardless of who's running it.

``` show_me_posts_people_like_me_have_liked()

- John saw 20 posts today and liked 9 of them.

- Cliff saw 20 posts today and liked 9 of them

- Jeff and Cliff had 6 overlapping likes

- Show Jeff the 2 extra posts Cliff liked; show Cliff the 2 extra posts Jeff liked

```

This seems like a simple / logical recommendation system. BUT the end result is that you make Jeff and Cliff closer to the same person over time. And times millions, you build echo chambers. And the biggest echo chambers (often those aligned with some identity politics) see they have a huge community and want to expand it. Making the whole platform worse as a byproduct.

Not the founder, but having run conversational agents at decent scale, I don't think the cost actually matters much early on.

It's almost always better to pay more for the smarter model, than to potentially give a worse player experience.

If they had 1M+ players there would certainly be room to optimize, but starting out you'd certainly spend more trying engineer the model switcher than you would save in token costs.

The problem here is the "so what?"

Imagine OpenAI is required by law to list their weights on huggingface. The occasional nerd with enough GPUs can now self host.

How does this solve any tangible problems with LLMs regurgitating someone else's work?

> should be playable on anything that has perl and a curses library (pretty much anything but Windows).

Maybe I'm missing something, but how do I play?