fern VS hnrss

Lots of these have been popping up lately, they all seem really good.

https://buildwithfern.com/

Fern | https://buildwithfern.com | Founding Backend Engineer | $160k + equity | On-site NYC | Full-time

At Fern, we're creating the modern developer experience platform. We work with developer-focused companies to generate SDKs & API documentation. We're looking for a Founding Backend Engineer to help us scale with our users. You'll join a small team (3 of us) and will be a product owner who designs, builds, and ships weekly.

Learn more at https://www.buildwithfern.com/careers

Fern (YC W23) | Founding Engineer | New York City | $130k-$160k + 0.5-1.0% equity | Full Time | Open Source | https://buildwithfern.com

REST APIs underpin the internet but are still painful to work with. They are often untyped, unstandardized, and out-of-sync across multiple sources of truth. With Fern, we aim to bring great developer experiences to REST APIs.

Our stack is Next.js + Vercel, Express (Node.js) + FastAPI (Python), Postgres DB + Prisma ORM, and AWS CDK. We're open source: https://www.github.com/fern-api/fern

We closed a Seed this year from top-tier US investors, including Y Combinator, Abhinav Asthana (Postman CEO), Arash Ferdowsi (Dropbox co-founder), and Ian McCrystal (Stripe's Head of Docs).

Learn more: https://www.buildwithfern.com/careers

Thank you for your encouraging words and insights!

There are indeed popular DSLs and code to openapi solutions out there. Many of which are easy to plug in to the openapi-stack libraries btw!

I guess I personally always found it frustrating to try to control the generated OpenAPI output using additional tooling and ended up preferring yaml + a visualisation tool as the api design workflow. (e.g. swagger editor)

But something like https://buildwithfern.com, or using zod as substitute for json schema may indeed be worth a try as a step before emitting openapi.

Fern (YC W23) | Founding Engineer | New York City | $125k-$175k + equity | Full Time | Open Source | https://buildwithfern.com

REST APIs underpin the internet but are still painful to work with. They are often untyped, unstandardized, and out-of-sync across multiple sources of truth. With Fern, we aim to bring great developer experiences to REST APIs.

Our stack is Next.js + Vercel, Express (Node.js) + FastAPI (Python), Postgres DB + Prisma ORM, and AWS CDK.

We closed a Seed this year from top-tier US investors, including Y Combinator, Abhinav Asthana (Postman CEO), Arash Ferdowsi (Dropbox co-founder), and Ian McCrystal (Stripe's Head of Docs).

Apply by emailing [email protected]

Hi HN! Langfuse is OSS observability and analytics for LLM applications (repo: https://github.com/langfuse/langfuse, 2 min demo: https://langfuse.com/video; try it yourself: https://langfuse.com/demo)

Langfuse makes capturing and viewing LLM calls (execution traces) a breeze. On top of this data, you can analyze the quality, cost and latency of LLM apps.

When GPT-4 dropped, we started building LLM apps – a lot of them! [1, 2] But they all suffered from the same issue: it’s hard to assure quality in 100% of cases and even to have a clear view of user behavior. Initially, we logged all prompts/completions to our production database to understand what works and what doesn’t. We soon realized we needed more context, more data and better analytics to sustainably improve our apps. So we started building a homegrown tool.

Our first task was to track and view what is going on in production: what user input is provided, how prompt templates or vector db requests work, and which steps of an LLM chain fail. We built async SDKs and a slick frontend to render chains in a nested way. It’s a good way to look at LLM logic ‘natively’. Then we added some basic analytics to understand token usage and quality over time for the entire project or single users (pre-built dashboards).

Under the hood, we use the T3 stack (Typescript, NextJs, Prisma, tRPC, Tailwind, NextAuth), which allows us to move fast + it means it's easy to contribute to our repo. The SDKs are heavily influenced by the design of the PostHog SDKs [3] for stable implementations of async network requests. It was a surprisingly inconvenient experience to convert OpenAPI specs to boilerplate Python code and we ended up using Fern [4] here. We’re fans of Tailwind + shadcn/ui + tremor.so for speed and flexibility in building tables and dashboards fast.

Our SDKs run fully asynchronously and make network requests in the background. We did our best to reduce any impact on application performance to a minimum. We never block the main execution path.

We've made two engineering decisions we've felt uncertain about: to use a Postgres database and Looker Studio for the analytics MVP. Supabase performs well at our scale and integrates seamlessly into our tech stack. We will need to move to an OLAP database soon and are debating if we need to start batching ingestion and if we can keep using Vercel. Any experience you could share would be helpful!

Integrating Looker Studio got us to first analytics charts in half a day. As it is not open-source and does not work with our UI/UX, we are looking to switch it out for an OSS solution to flexibly generate charts and dashboards. We’ve had a look at Lightdash and would be happy to hear your thoughts.

We’re borrowing our OSS business model from Posthog/Supabase who make it easy to self-host with features reserved for enterprise (no plans yet) and a paid version for managed cloud service. Right now all of our code is available under a permissive license (MIT).

Next, we’re going deep on analytics. For quality specifically, we will build out model-based evaluations and labeling to be able to cluster traces by scores and use cases.

Looking forward to hearing your thoughts and discussion – we’ll be in the comments. Thanks!

[1] https://learn-from-ai.com/

[2] https://www.loom.com/share/5c044ca77be44ff7821967834dd70cba

[3] https://posthog.com/docs/libraries

[4] https://buildwithfern.com/

You can recommend it in what context, from openapi (as they claim https://github.com/fern-api/fern#starting-from-openapi ) or from their ... special ... definition schema?

For those wanting less talk, moar code: https://github.com/fern-api/fern-java/blob/0.4.2-rc3/example... -> https://github.com/fern-api/fern-java/blob/0.4.2-rc3/example...

I'm one of the builders of an open source project (buildwithfern.com) to improve client codegen. One of the learnings I've had is that the quality of OpenAPI specs varies widely (like really widely). We wrote a linter that suggests improvements to your OpenAPI before you run the code generators and that's been really helpful for generating idiomatic clients.

You can try Fern for free: https://buildwithfern.com

That’s interesting.

I have predictive models that can predict if a headline (w/o the rest of the article and not considering the URL) will (a) get more than 10 votes and (b) if it does get more than 10 votes will the votes/comments ratio be more than 2 (which is roughly average)

The first model gets a ROC-AUC (see https://scikit-learn.org/stable/modules/generated/sklearn.me...) in the low 60’s (not good, the second model gets in the low 70’s (actually pretty good though it is a heat seeking missile for clickbait headlines) and my latest content-based recommender for RSS items gets almost 80. (I saw a paper that one system at TikTok gets about 85)

To do all that you need about 10,000 headlines and don’t get a lot of benefit from having more than 100,000. The ceilings on performance have more to do with the nature of the problem rather than my models: the same article can get submitted twice and get 0 votes one time and 200 the other time so it can never be as accurate as “is this an article about galactic astronomy?”

I had it ingest the HN comments firehose and found the amount of articles was overwhelming, my YOShInOn RSS reader now ingests the “best comments” from

https://hnrss.github.io/

together with 110 other feeds and actually I like the comments it picks out a lot. Now that the system is adding about 3000 items per day it might be able to handle a big feed like the comments firehose since now those comments are diluted with so many quality articles. For a problem like that you might want a two-score system with: (i) is it relevant? (something I like) and (ii) is it popular? (like Google’s PageRank)

I think you could make a model that compares comments in the best comments feed with other comments. I have tried formulating the problems above as regression problems where I try to predict the actual score and it does not work well because of the uncertainty problem but formulated as a classification problem for a score over a threshold it is easy to make a well-calibrated model that tells you “this article has a 20% chance of frontpaging” which is about the best anyone can do.

Subscribe via rss, so you can scratch the curiosity itch and each the FOMO, without coming to the site all the time and looking over the same things 20 times?

https://hnrss.github.io/

https://news.ycombinator.com/item?id=9491978

and this https://hnrss.github.io/

ps i’m ok with some % of false positives, but hopefully a sprinkle of OpenAI could keep that magically low?

thanks

It sounds interesting but I use https://hnrss.github.io/

Unless it had most of the features of hnrss.org I would not be able to use it.

Perhaps you could pivot your approach and submit a PR to hnrss for the feature?

Looks like there's an unmerged PR on the third-party hnrss project that would add this: https://github.com/hnrss/hnrss/pull/84

Check out below link to get a more customized, topic wise rss feeds.

https://hnrss.github.io/