justintorre75

Joined 4 years ago

Karma

109

Submissions

21

Member since

Oct 2

View on Hacker News

Recent submissions

Helicone allows users to write SQL directly to a shared ClickHouse justintorre.com

11 justintorre75 3 months ago 3 comments

Show HN: AI Trolley Problem Arena aitrolleyproblem.com

9 justintorre75 10 months ago 2 comments

Comment · 1 year ago

MCP Agent seems super promising and the team behind it is amazing!

Show HN: Helicone (YC W23) – OSS LLM Observability and Development Platform github.com

29 justintorre75 1 year ago 7 comments

LLM Stack Guide helicone.ai

4 justintorre75 1 year ago 1 comments

Comment · 2 years ago

A lot of people are asking how to automate their data flywheel. With Helicone + OpenPipe it has never been easier. With 2 lines of code, your app gets better over time without you needing to know how to finetune your own model.

Finetuned LLMs with 2 lines of code. Helicone + OpenPipe helicone.ai

1 justintorre75 2 years ago 1 comments

Comment · 3 years ago

This is exactly right, thanks a bunch for checking. Also, thanks for the note! We will add a SECURITY.md

Comment · 3 years ago

Yeah this was added by accident, luckily we have pretty good management of local development and production testing, so these keys were not production keys

Comment · 3 years ago

Thanks! Please reach out to the team on discord if you have any questions

Comment · 3 years ago

Thanks! :D No need to bring your own logger, just change one line of code and then all your logs are in Helicone.

We are using CF Worker cache under the hood https://developers.cloudflare.com/workers/runtime-apis/cache...

We might use D1 for some of our other features like rate limiting.

Comment · 3 years ago

Great question! The short answer is nothing! We just have to out pace them and make sure we develop a better product experience.

Two key advantages that we have over OpenAI. 1. We are open source and are trying to build a community of developers that can out run any single LLM provider. 2. We are completely provider agnostic, which allows us to aggregate and share common features across tools. (One analogy we like to use, is we want to emulate how dbt is database agonistic, and Helicone will grow to be provider agnostic)

Comment · 3 years ago

Couldn't agree more. Thanks! :)

Comment · 3 years ago

These are great! we looked into using reflare as well, however reflare does not support streaming at the moment. We are looking to give back to the community and add it for them.

I opened this issue up last week https://github.com/xiaoyang-sde/reflare/issues/443

Comment · 3 years ago

stay tuned for updated pricing