Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

About AI Evals

hamel.dev

Post reply on HN
Print view View original

31–40 of 46 posts

Re: About AI Evals

#31

Post by dbish »

ReDeiPirati wrote: post #23

> Q: What makes a good custom interface for reviewing LLM outputs? Great interfaces make human review fast, clear, and motivating. We recommend building your own annotation tool customized to your domain ... Ah! This is a horrible advice. Why should you recommend reinventing the wheel where there is already great open source software available? Just use https://github.com/HumanSignal/label-studio/ or any other type o…

I think the truth is somewhere in between. I find label studio to be lacking a lot of niceties and generally built for very the average text labeling or image labeling use case, but anything else (like a multi-step agent workflow or some sort of multi-modal task specific problem) it is not quite right for and you do end up doing a bit of trying to build your own custom interface.

So, imho you should try label studio but timebox and really decide for yourself quickly if it's going to work for you in a day, and if not go vibecode a different view and try it out or build labeling into a copy of a front end you're already using for your task if that's quick.

What I think we really need here is a "lovable meets labelstudio" that starts with simple defaults and lets anyone use natural language, sketches, screenshots, to create custom interfaces and modify them quickly.

Re: About AI Evals

#32

Post by dbish »

Hamel has really great practical eval advice and I always share his advice and posts to any new teams developing AI features/agents/assistants that I'm working with, both internally and with new startups in the AI applications space.

What I'd love to see one day is a way to capture this advice in a "Hamel in a box" eval copilot, or the agent that helps eval and improve other ai agents :). An eval expert who can ask the questions he's asking, look at data flowing through your system, make suggestions about how to improve your eval process, and automatically guide non experts into following good practices for their eval loop.

Re: About AI Evals

#33

Post by simonw »

satisfice wrote: post #21

This reads like a collection of ad hoc advice overfitted to experience that is probably obsolete or will be tomorrow. And we don’t even know if it does fit the author’s experience. I am looking for solid evidence of the efficacy of folk theories about how to make AI perform evaluation. Seems to me a bunch of people are hoping that AI can test AI, and that it can to some degree. But in the end AI cannot be accountable…

Hamel wrote a whole lot more about the "LLM as a judge" pattern (where you use LLMs to evaluate the output of other LLMs) here: https://hamel.dev/blog/posts/llm-judge/

Re: About AI Evals

#34

Post by _jonas »

Evals are critical, and I love the practicality of this guide!

One problem not covered here is: knowing which data to review.

If your AI system produces say 95% accurate responses, your Evals team will spend too much time reviewing production logs to discover different AI failure modes.

To enable your Evals team to only spend time reviewing the high-signal responses that are likely incorrect, I built a tool that automatically surfaces the least trustworthy LLM responses:

https://help.cleanlab.ai/tlm/

Hope you find it useful, I made sure it works out-of-the-box with zero-configuration required!

Re: About AI Evals

#35

Post by hamelsmu »

_jonas wrote: post #34

Evals are critical, and I love the practicality of this guide! One problem not covered here is: knowing which data to review. If your AI system produces say 95% accurate responses, your Evals team will spend too much time reviewing production logs to discover different AI failure modes. To enable your Evals team to only spend time reviewing the high-signal responses that are likely incorrect, I built a tool that auto…

Hamel here. Thanks so much for asking this question! I will work on adding it to the FAQ. Please keep these coming!

Re: About AI Evals

#36

Post by hamelsmu »

simonw wrote: post #33
satisfice wrote: post #21

This reads like a collection of ad hoc advice overfitted to experience that is probably obsolete or will be tomorrow. And we don’t even know if it does fit the author’s experience. I am looking for solid evidence of the efficacy of folk theories about how to make AI perform evaluation. Seems to me a bunch of people are hoping that AI can test AI, and that it can to some degree. But in the end AI cannot be accountable…

Hamel wrote a whole lot more about the "LLM as a judge" pattern (where you use LLMs to evaluate the output of other LLMs) here: https://hamel.dev/blog/posts/llm-judge/

Appreciate it, Simon! I have now edited my post to include links to "intro to evals" for those not familiar.

Re: About AI Evals

#37

Post by hamelsmu »

dbish wrote: post #32

Hamel has really great practical eval advice and I always share his advice and posts to any new teams developing AI features/agents/assistants that I'm working with, both internally and with new startups in the AI applications space. What I'd love to see one day is a way to capture this advice in a "Hamel in a box" eval copilot, or the agent that helps eval and improve other ai agents :). An eval expert who can ask t…

I think that will be very possible soon! We continue to write about it publicly :) Also thanks to my friends and colleagues who write a lot on this subject that I frequently collaborate with:

- Shreya Shankar https://www.sh-reya.com/ - Eugene Yan https://eugeneyan.com/ - Bryan Bischof https://bio.site/Docdonut

Re: About AI Evals

#38

Post by ultrasaurus »

dbish wrote: post #31
ReDeiPirati wrote: post #23

> Q: What makes a good custom interface for reviewing LLM outputs? Great interfaces make human review fast, clear, and motivating. We recommend building your own annotation tool customized to your domain ... Ah! This is a horrible advice. Why should you recommend reinventing the wheel where there is already great open source software available? Just use https://github.com/HumanSignal/label-studio/ or any other type o…

I think the truth is somewhere in between. I find label studio to be lacking a lot of niceties and generally built for very the average text labeling or image labeling use case, but anything else (like a multi-step agent workflow or some sort of multi-modal task specific problem) it is not quite right for and you do end up doing a bit of trying to build your own custom interface. So, imho you should try label studio…

The SaaS version of Label Studio does have a natural language interface to create custom interfaces: https://docs.humansignal.com/guide/ask_ai

I'm ostensibly an expert in the product and I probably use that 90%+ of the time (unless I'm testing something specific) -- using a sketch as input is a cool idea though!

Disclaimer: I'm the VP Product at HumanSignal the company behind Label Studio.

Re: About AI Evals

#39

Post by ethan_smith »

andybak wrote: post #10

> About AI Evals Maybe it's obvious to some - but I was hoping that page started off by explaining what the hell an AI Eval specifically is. I can probably guess from context but I'd love to have some validation.

AI Evals are systematic frameworks for measuring LLM performance against defined benchmarks, typically involving test cases, metrics, and human judgment to quantify capabilities, identify failure modes, and track improvements across model versions.

Re: About AI Evals

#40

Post by petesergeant »

satisfice wrote: post #21

This reads like a collection of ad hoc advice overfitted to experience that is probably obsolete or will be tomorrow. And we don’t even know if it does fit the author’s experience. I am looking for solid evidence of the efficacy of folk theories about how to make AI perform evaluation. Seems to me a bunch of people are hoping that AI can test AI, and that it can to some degree. But in the end AI cannot be accountable…

> This reads like a collection of ad hoc advice overfitted to experience that is probably obsolete or will be tomorrow

Even if it is (and very specifically I don't think it is), you've got to start somewhere, and I've not seen advice better than Hamel's kicking about anywhere. His writing helped me get my start on my own evals some months ago, for sure.

Post reply on HN