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

21–30 of 46 posts

Re: About AI Evals

#21

Post by satisfice »

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 for such testing, and we can never know all the holes in its judgment, nor can we expect that fixing a hole will not tear open other holes.

Re: About AI Evals

#22

Post by Onawa »

mbanerjeepalmer wrote: post #18
calebkaiser wrote: post #7

I'm biased in that I work on an open source project in this space, but I would strongly recommend starting with a free/open source platform for debugging/tracing, annotating, and building custom evals. This niche of the field has come a very long way just over the last 12 months, and the tooling is so much better than it used to be. Trying to do this from scratch, beyond a "kinda sorta good enough for now" project, i…

Yes I'm not sure I really want to vibe code something that does auto evals on a sample of my OTEL traces any more than I want to build my own analytics library. Alternatives to Opik include Braintrust (closed), Promptfoo (open, https://github.com/promptfoo/promptfoo ) and Laminar (open, https://github.com/lmnr-ai/lmnr ).

I've used and liked Promptfoo a lot, but I've run into issues when trying to do evaluations with too many independent variables. Works great for `models * prompts * variables`, but broke down when we wanted `models * prompts * variables^x`.

Re: About AI Evals

#23

Post by ReDeiPirati »

> 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 of open source annotation software you want to get started. These tools cover already pretty much all the possible use-cases, and if they aren't you can just build on top of them instead of building it from zero.

Re: About AI Evals

#24

Post by mmanulis »

pamelafox wrote: post #19

Fantastic FAQ, thank you Hamel for writing it up. We had an open space on AI Evals at Pycon this year, and had lots of discussion around similar questions. I only wrote down the questions, however: # Evaluation Metrics & Methodology * What metrics do you use (e.g., BERTScore, ROUGE, F1)? Are similarity metrics still useful? * Do you use step-by-step evaluations or evaluate full responses? * How do you evaluate VLM (v…

Any chance you can share what the answers were for choosing an evaluation framework?

Re: About AI Evals

#25

Post by abletonlive »

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…

This awful advice can’t be blanket applied and misses the point: starting from zero is extremely easy now with LLMs, the last 10% is the hardest part. Not only that, if you don’t start from zero you aren’t able to build from whatever you think the new first principles are. Spacex would not exist if it tried to extend old paradigm of rocketry.

There’s nothing wrong with starting from scratch or rebuilding an existing tool from the ground up. There’s no reason to blindly build from the status quo.

Re: About AI Evals

#26

Post by ReDeiPirati »

abletonlive wrote: post #25
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…

This awful advice can’t be blanket applied and misses the point: starting from zero is extremely easy now with LLMs, the last 10% is the hardest part. Not only that, if you don’t start from zero you aren’t able to build from whatever you think the new first principles are. Spacex would not exist if it tried to extend old paradigm of rocketry. There’s nothing wrong with starting from scratch or rebuilding an existing…

I'd have agreed with you, if the principles would be different. But what was showed in the content is EXACTLY what those tools are doing today. Actually those tools are way more powerful and considering & covering way more scenarios.

> There’s nothing wrong with starting from scratch or rebuilding an existing tool from the ground up. There’s no reason to blindly build from the status quo.

Generally speaking all the options are ok, but not if you want to have something up as fast as you can or if your team is piloting something. I think the time you spend to vibe code it is greater than to setting any of those tools up.

And BTW, you shouldn't vibe code something that flows proprietary data. At least you would work with co-pilots

Re: About AI Evals

#27

Post by jph00 »

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…

Label Studio is great, but by trying to cover so many use cases, it becomes pretty complex.

I've found it's often easier to just whip up something for my specific needs, when I need it.

Re: About AI Evals

#28

Post by th0ma5 »

People should be demanding consistency and traceability from the model vendors checked by some tool perhaps like this. This may tell you when the vendor changed something but there is otherwise no recourse?

Re: About AI Evals

#29

Post by hamelsmu »

pamelafox wrote: post #19

Fantastic FAQ, thank you Hamel for writing it up. We had an open space on AI Evals at Pycon this year, and had lots of discussion around similar questions. I only wrote down the questions, however: # Evaluation Metrics & Methodology * What metrics do you use (e.g., BERTScore, ROUGE, F1)? Are similarity metrics still useful? * Do you use step-by-step evaluations or evaluate full responses? * How do you evaluate VLM (v…

This is Hamel. Thanks for sharing! I will incorporate these into the FAQ. I love getting additional questions like this.

Re: About AI Evals

#30

Post by bbischof »

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…

Label studio is fine if it covers your need, but in many cases the core opportunity in an eval interface is fitting in with the SME’s workflow or current tech stack.

If label studio looks like what they can use, it’s fine. If not, a day of vibecoding is worth the effort to make your partners with special knowledge comfortable.

Post reply on HN