bosky101

thanks, fixed

programmatic logistics?

    mv $HOME/ship/spanish-jersey $HOME/ship/work

    mv $HOME/ship/cooler mv $HOME/ship/darkstore1/

    for i in `ls $HOME/ship/winter-clothes/*` ; do mv ...

~Bosky

i created https://nonfungibledocs.com using few concepts of ab testing and natural language processing. basically from a single doc or email - if you create as many subtle variants (of prepositions or grammatical or punctuation) if any of the 2000 leak, then you can even from a single page of a leak - reverse engineer who was the leak.

If anyone wants an s3 browser with folder counts, and object rendering based on its extension, dm.

i've never had situations where i prompt and had to go out for coffee or a walk or drive. one shotting - your first prompt. perhaps.

but like a person - when the possibility of going off in the wron g direction is so high, i've always had 1 - 2 line prompts, small iterations much more appealing. The only times i've had to rollback would be when i run out of credits, and a new model cant deal with the half baked context, errors, refactoring.

The right link is https://github.com/vrn21/bouvet

@logan waiting for named apikeys

Rye allows you to even enter shipping info and pay for the product. But I can't help but feel it hasn't got the traction it deserves.

1) Are there plans to allow Devs to do the same?

2) why wouldn't you open the limit beyond 1000 free as long as you are making a rev share

3) does this pick from Shopify products/stores?

Imo the agentic loop isn't really closed unless you allow agents to pay and paywalls today aren't agent friendly. Tokenized cards, 16 digital cards. Perhaps but this involves high trust from users. Which means you are left with guiding users to the link and hoping they buy the product.

4) partnering with merchants where cards are already tokenized maybe your best converting potential customer base. But it's easy to do evil here, or loose trust without guardrails.

5) I would come up with a process to incentivize adding products to the ecosystem. However tiny the reward.

Lot of opportunity. Nice pitch. Good luck!

Would try this out of you can increase the 1k limit to something that is a win:win

As a consumer I'm asking myself why not just make an extension. I can see myself trying and picking 2 or more browser addons to to turbo charge + chat with any page.

From a founder hat, I can see why the code base is a moat, hard problem. I hope the effort is worth the cost.

Good luck.

Very impressive that you were able to pull this off. And kudos for open sourcing it.

Q: is it possible to have the bot speak?

For someone not familiar with this culture, i for a moment thought the thread was talking about Sylvester Stallone.

RIP.

Was sly involved in the song superstition?

Kudos, about time, Exciting news.

Your first 2 examples on your readme involve single agents. These are a waste of time. We don't need yet another llm api call wrapper. An agentic system with just 1 tool / agent is pointless.

Thankfully your third example half way down does have an eg with 3 agents. May have helped to have a judge/architect agent.

Not clear about the infra required or used.

Would help to have helper functions to get and set session state/memory. Being able to bootstrap from json could be a good feature.

Would help to have diff agents with diff llms to show that you have thought things through.

Why should spawning 1000's of agents even be in your benchmark. Since when did we start counting variables. Maybe saying each agent would take X memory/ram would suffice - because everything is subjective, can't be generalized.

Consider a rest api that can do what the examples did via curl?

Good luck!

For unproven entrepreneurs, YC is the best bet.

Confident and serial entrepreneurs are able to raise with just an idea/meeting because there is some precedence.

But there is a silver lining.

You don't need funding to startup.

If you do anything that gets a lot of users using it. I guarantee you investors will be the ones chasing you.

Would have been good if the familiar navbar would have been retained. Btw /show gave 404. Trivial to support those urls. The filters were too tough to find.

Yes, anyone can apply. But it's important to refrain from over engineering how it's built, what framework or what model. These are all secondary for a startup.

MVP matters.

Customer traction outweighs all.

Getting folks to pay for AI is challenging. If you manage to crack a niche and do so and pay or pre-order - that will give you an understanding and core tenant that is expected from companies to scale once they get accepted into YC.

It's tougher to get the average chatgpt free user - to pay for an unknown startup. All you need is one company to agree to pay. Because if you can get 1 (not friends & family), you get 10. And then get 100.

If I were you, my #1 focus for the entire team would be to get 1 company to pay, before starting to build or touch code. Get the initial NO's to tweak every cold call/email/pitch refining every day until you crack your first deal. I would stay away from long tail consumers.

Good Luck!

"Karen, can you print, scan and mail me a copy of our NDA policy for our non-external internal employees"

Sorry for the offtopic post, but I am looking to hire someone with 10 years of experience with is-even-ai. Urgent. Your first unpaid assignment will be to help load balance a bunch of MCP servers to add and THEN check if it's even. So much to go from here! We're a single threaded GPU first identity operator company with a lot history of returning the same thing. We're now expanding to combine and add multiple things. In 6 months of SOTA fine tuning we can already add upto 3 numbers. An MCP first. With temperature 1 we even add random numbers. An industry first. And we're just getting started. Join us. We're adding to our team!

Rofl

Try searching google for

    Birthday card template
    Event rsvp template
    Restaurant menu template

Your homepage has no screenshots to inspire confidence to signup. All links/buttons just jump to signup. Maybe add ^ video to improve conversion.

Also having nothing open source on GitHub was unexpected but understandable. It's ok to be private for a private company. It's just that the entire ecosystem is open source. A day may come when it's strange not to have code running on your laptop to be open source. But it's totally your call.

PS: you should spend some money on a designer. Too many margins and wastage of space in your demo app. And adding some polish could go a long way in adoption/fomo/conversion.

Followed on x.

Good luck!

Your readme doesn't mention any example of multiple agents. We don't need another wrapper to anthropic/openai/*. Without being able to select between multiple tools/agents - you only need 2 lines of code to achieve llm calls, and another 2 lines for state management.

That said the interface is more idiomatic that others agent frameworks that show up here.

It also wasn't clear where the last N messages is being persisted. Db/file/adapters/?

Good luck!

Well done!

I would add a hamburger menu to show other links like a sample invoice, blog , pricing , login , etc

Canva gets free traffic because it creates kinds of slides. Maybe you could do the same.

I drew a cartoon/satire on mcp titled zombie prompting. You can find the original here https://x.com/0xBosky/status/1906356379486679521

Tldr; it's json array passed to llms. Swagger would have sufficed. How and why youcome up with the array shouldn't matter. We shouldn't need 10000 redundant servers.

I'd like to remind you that tools is a json array to any modern llm inference api. That rather than returning text, tells you which function to call.

I'm all for abstraction of a level of indirection. But this is pushing things too far.

We now have an entire ecosystem, layers of unneeded engineering, cohorts of talent and capital going to create man in the middle servers that forces us to get this array from around the world + maintain a server with several gb of deps to get a json array that you should't trust.

2) It makes sense if every server has a tools.txt equivalent of their own swagger. Eg i would trust google photos to maintain and document their tools rather than the 10,000 MCP servers possibly alive for no reason and already out of date by the time you are done reading this comment. In addition to being over engineered, to trust a random server as a proxy never made any sense.

3) nobody wants to run servers. Can't find this meme, but found it here on HN several times.

Sorry but I would rather not wait a year for this industry to crash and burn and take down genai apps galore or worse, start leaking this data and your bills.

Kudos to document any security gaps though.

Great job with the core product. The MCP update isn't as interesting honestly.

I'm saying there are too many things to learn to get even a simple example let alone a real world example going. Have a look at their examples at https://docs.hatchet.run/home/conditional-workflows

Here is my feedback after spending 15 mins on your docs.

Nice work on the lite mode, open source, logging, dx interface.

You may want to replace Hello world examples with real world scenarios.

The workflows that involve multiple steps tasks, dag in your terminology - the code simply isn't intuitive.

You now have to get into the hatchets mindset, patterns, terminology. Eg: the random number example is riddled with too many. How many of the logos on your homepage did you have to write code for? Be honest.

Knowing to program should be 90% enough. Eg for js:

   // send("hi", user => user.signed_up_today)
   //  .waitFor("7d")
   //  .send("upgrade", user => !user.upgraded)

An engineering post on what's under the hood makes sense. But customers really don't care about your cloud infra flexes in a post introducing your company pitching the product. It's just koolaid.

Same with complete rewrite so early. I'm glad you are open to change. But the workflow market today with so many options, i don't belive this is the last rewrite or pivot to come.

The DAGs itself aren't very readable. You are better off switching to something like react flow that lets you nocode edit as well.

Focus on automation journeys that are common. Like cookbooks. And allow folks to just import them or change some configurations. like drip marketing, renewals, expired cards, forgot password handlers, shortlink creators, maybe pdf merging, turning a bunch of saved links to a daily blog post, etc

How does a workflow replace a saas they are paying $99 for. That's powerful.

Tough to serialize a worflow to json . Or atleast didn't see it. this makes it easy to have workflows as code, create nocode editors in your own roadmap. You want people to hop from 1 company to another taking their hatchet workflows with them

Good luck, and sorry for coming off as rude. It's just a space I am very passionate about.

OMG!

We need a way to collapse comments on HN