Hacker News

Top stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Fixing the Portobello Police Station Clock(pointinthecloud.com)
    23comments
  2. Gemini 3.8 text-to-speech says hello(blog.google)
    18comments
  3. GPT-6 Astra has gained the ability to drive a car(drivingbench.com)
    81comments
  4. Stripe's Knowledge AI Platform(stripe.dev)
    50comments
  5. Strands Harness(strandsagents.com)
    44comments
  6. Radicle: Disclosure of Vulnerability in the Network Protocol(radicle.dev)
    7comments
  7. Jev Can't Be Calibrated(alexmolas.com)
    29comments
  8. Jev in 25 Lines of Python(nobodywho.ai)
    143comments
  9. Claude Code reads AGENTS.md only when telemetry is on [fixed](szypowi.cz)
    196comments
  10. GPT-6 Sol and Luna(openai.com)
    802comments
  11. Z80 REPL (2018)(abagames.github.io)
    12comments
  12. I don't want the details(michaelheap.com)
    114comments
  13. Claude Opus 5.5(anthropic.com)
    1034comments
  14. Tokens Too Cheap to Meter(jyn.dev)
    82comments
  15. QuestDB (YC S20) Is Hiring a Sales Engineer(questdb.com)
    discuss
  16. Woman Arrested, Dragged Away After Speaking About Flock at City Council Meeting(404media.co)
    57comments
  17. Web-based IBM 1620 emulator and IPL-V from 1963(github.com/pkimpel)
    3comments
  18. The GitHub wiki is an anti-pattern (2022)(michaelheap.com)
    68comments
  19. OpenAI GPT–6 Astra breaks Enigma message that has resisted solution since 2005(cryptocellar.org)
    417comments
  20. Transit rewards(waymo.com)
    271comments
  21. Seattle City Council votes to ban surveillance pricing in sale of groceries(consumerreports.org)
    6comments
  22. Microsoft killed FoxPro in 2007. Anyway, here's FoxPro revived(foxscript.org)
    232comments
  23. What California is learning from solar panels built over irrigation canals(kqed.org)
    584comments
  24. How did AMD Ryzen get 50% faster in two years?(lemire.me)
    175comments
  25. ReBarUEFI: Resizable BAR for almost any UEFI system(github.com/xcuri0)
    64comments
  26. 'We hacked the FBI:' Hackers say they have data on all FBI employees(404media.co)
    537comments
  27. Samsung accidentally freezes its smart fridges with a software update(androidauthority.com)
    186comments
  28. SAML: A fractal of bad design(trailofbits.com)
    160comments
  29. Socialism's Positive Rating Tops 40% for First Time(gallup.com)
    37comments
  30. Data-only attacks are easier than you think (2024)(usenix.org)
    32comments

Stripe's Knowledge AI Platform

96 pointsby 3h agostripe.dev
52 comments
2h agoHN ↗

TIL people still fall for eh I mean use Langchain. Sorry, low value comment; I don’t know how to do that differently; it is such bad garbage since day one and strangely it did not improve. Sorry anyway for the comment, at least it was not LLM generated?

1h agoHN ↗

Yes, I also thought it's crap the moment I saw they need langchain to develop a harness.

1h agoHN ↗

The fact that Stripe are touting a production product that (at face value) benefits their business seems to suggest that maybe crap is subjective and as ever, being overly opinionated in an emerging space might actually be a blocking mindset rather than a positive one.

1h agoHN ↗

It might also suggest they went with the first LLM recommendation, like Anthropic choosing React for Claude Code.

1h agoHN ↗

To make your comment more high value, could you explain why you think langchain is bad?

1h agoHN ↗

It (and most other systems) abstract the wrong concepts when you want to create an agent. They promote what was likely never a great strategy but even parsimoniously what are strategies that were good ideas months or a year back.

For example how langchain or whatever else handles subagents and deep research is laughable even today.

So whats the recommendation? Just use pydantic and code everything up yourself. Maybe strands I dont know.

56m agoHN ↗

Which specific strategies do you think are outdated, and what would you recommend instead? This sounds more like a criticism of older versions of LangChain than its current APIs. The post also uses deepagents, a separate package in the same ecosystem. Is there something in the current implementation of either that you’re referring to?

1h agoHN ↗

Instead of spending half the comment reflecting on your post why not point out what you don’t like about it or some better alternatives?

1h agoHN ↗

I have a hard time keeping up with the space. Is langchain old news? Is there a page that kind of shows what the status quo for tooling is?

1h agoHN ↗

+1 would love to know as well. I have generally found the open source space to be lacking in this area and hoping it catches up!

1h agoHN ↗

There's like 1000 langchain alternatives and none are good, they're all vibe-coded unstable projects.

I use Apache Burr but it's not as good as LangChain. I just don't want to use software whose website has a pricing page if it's not a SAAS.

1h agoHN ↗

Totally, I find LangChain is the Vercel of ML

43m agoHN ↗

It's a lot of sugar and high level abstractions on top of existing things, I find using the existing things not that complicated or difficult and I struggle to see the value on using the framework as it doesn't sit well with my way of abstracting the stack.

1h agoHN ↗

Ahhh I built an internal set of agents to run our company (finances, all info in the karpathy-style LLMWiki and a database of clients, contracts, billing, time tracking, all managed by MCPs, etc) and it's also called Kai (company name is Kaizen)

Happy to be in such good company!

1h agoHN ↗

All hand written or did you have any underlying libraries that you used?

16m agoHN ↗

Mostly custom. Full data model and full web and mobile app to help run day to day operations.

The agent has switched a few times, initially NanoClaw, then Hermes, and now Vercel's Eve (maximum customizability).

NextJS/Shadcn web app, postgres db, eve agent layer, MCP tools (over 100 so every single thing can be done by an agent), SwiftUI mobile app, etc.

Integrations with gmail, gcal, gdrive, quickbooks, using mdx for the wiki displays (so we have rich diagrams, 3d models, etc).

We write about it here: https://kznconsulting.com/work/how-we-run-kaizen

1h agoHN ↗

I read a buzz word "Knowledge AI Platform" but I did not see any specific feature helpful for knowledge management like verification or transparency. It is more like any generic Agent builder. Maybe it meant to justify building something internally.

1h agoHN ↗

None of these have been especially impressive.

I think that’s because none of them go past “I’ve set up agents to be orchestrated this way” and that’s about as impressive as “look at my cloudformation template”.

1h agoHN ↗

This site could use a bit more line height, more paragraphs, or less text overall.

1h agoHN ↗

Somebody probably mentioned this already or maybe its just me but: The "endless scroll" this page does is neat, to say the least.-

1h agoHN ↗

[Bad mental image ... can't unsee ...] :)

53m agoHN ↗

There's quite a bit of cool stuff in the console too! The one in the top right corner

1h agoHN ↗

oh not these guys again. These are just so idiotic.

Spotify built some nonsense like this too and made ridiculous claims that it saves 90 percent of tokens. I guess anything goes these days.

1h agoHN ↗

Size and scale, I would think. An out of the box solution probably doesn't quite have the same capabilities as something they can (and now have to) manage in it's entirety.

Stripe probably WANTS to be opinionated about how their company works with the tools.

1h agoHN ↗

In the first paragraph:

No existing tool could handle the data security requirements and specific workflows Stripe needed

1h agoHN ↗

Dammit, I just named my newborn son Kai.

1h agoHN ↗

Very cool demonstration of managed agents built for the needs of their own business.

I think this is where a lot of companies are going to go: on-prem platforms that give various teams access to agents that are as powerful as coding agents, but much more managed and governed.

I'm betting on this with my open source project, Lightspeed: https://github.com/smartcomputer-ai/lightspeed

1h agoHN ↗

Your project seems way better than the stuff they built, nice work.

1h agoHN ↗

I like it, very smart for agents at scale.

33m agoHN ↗

You wrote your readme yourself. It shows. So refreshing and i was able to finish it too.

2m agoHN ↗

Thank you. Yes, I did. There might be some AI-isms in there, because agents just can’t help themselves to dump their arcanae in there.

19m agoHN ↗

Wow, where do you work? Can we talk? Looking for smart people!

1h agoHN ↗

Dang it, I just named my newborn son Kai. At least I didn’t go with Alexa..

48m agoHN ↗

It’s a cool name! Don’t let Stripe make you doubt that haha

36m agoHN ↗

Don't worry, thanks to nominative determinism, you've secured your kids employment years in advance

1h agoHN ↗

The article reads like slop, to be honest.

49m agoHN ↗

It's very close to the direction we're taking for windmill.dev, we call it "operator builders" rather than focus on "knowledge graph" which the article is very light on details of.

What I'm mostly reading is a developer platform and runtime where users can build agents that can run tools and for that you need a secure code runtime, ACL/permissions, easy way to build apps or what cloudflare OS call gadgets. We're betting on this too at https://github.com/windmill-labs/windmill, very curious to see if that's the future for most enterprise and if a model where everyone vibe-code/fork cloudflare OS to their enterprise need is the future, or a more exhaustive/enterprise platform like ours does.

38m agoHN ↗

haha stripe's example prompt is "Create an event"

33m agoHN ↗

Stripe is the company I usually hold up as the exemplar of polished internal tools. Hopefully this is taken the right way and I don't want to be negative towards the teams working on this, but I see a distinct lack of polish in these tools and presentations. Some examples:

- Unnecessary AI copy throughout the interfaces like "Browse, discover, and manage skils for your agents", "No favorites yet — hover a card and click the star to pin it here", "One execution environment, shared across agents". These instantly read as AI copy and decrease my enthusiasm.

- Inconsistent, AI-sloppy look-and-feel with different typefaces spattered across the interface

- The session metrics slide looks busy and AI-generated. It repeats 360,014 sessions in one of the cells at the top, but also has a "360K sessions" in the heading

I don't know if I'm the only one that notices this stuff, or whether others see it too.

30m agoHN ↗

Stripe is the company I usually hold up as the exemplar of polished internal tools.

unless you work there how would you know this?

28m agoHN ↗

They have published a bunch of stuff about their internal tools in the past. Look up https://stripe.com/blog/stripe-home and compare it to this, as an example.

It's always possible that in reality they were always a bit less polished behind the scenes though.

32m agoHN ↗

Somewhat interesting how the design of Stripe's developer-focused landing pages used to be the "cream of the crop," so to speak, but now they just look like Claude run amok. I wonder if the web design "skills" for Claude, and other LLMs, were overly trained on Stripe.

25m agoHN ↗

Within two weeks of our April launch, most of Stripe was using Stripe's Knowledge AI Platform, also known as Kai.

By force or by choice?

1m agoHN ↗

By choice. I currently work at Stripe (opinions my own, I'm just some guy) and was here when it released. It's a genuinely useful tool, which explains the widespread adoption.

13m agoHN ↗

Hope this comes over as constructive criticism:

  1. The whole interface feels way too vibe coded with tons of unneeded stuff. Why does it have a console and snake game built in? Why does it have annoying sounds? Why is it full of AI slop writing? The latter is especially confusing because the first person listed under authors is a "Technical Writer". I guess the interface is the general stripe.dev page not exactly related to Kai but the post definitely is pure AI slop writing.
  2. It seems to claim things that might not be substantiated like the following: "When Account Executives use Kai, they produce 2x the sales activity, create 17% more opportunities, generate 26% more revenue opportunities, and close 39% more deals when compared to the same sellers in weeks they don't use it." Correlation is not causation. More engaged, better sales people might just also use more tools like this one, it doesn't mean all the increase in sales is because of the tool.
  3. the post talks a lot about how great this tool is but it describes nearly nothing of value to the outsider who can't access it. What were the valuable lessons learned? What's neat about it? There is not much meat imho.

It doesn't live up to my usual expectations from Stripe.

10m agoHN ↗

I want to read this, but the ever-changing linear gradient of the background is too visually distracting. I tried to get around it by highlighting text I want to read, but since the background is changing underneath it, so is the highlight. My eyes hurt.