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

Launch HN: Traceloop (YC W23) – Detecting LLM Hallucinations with OpenTelemetry

news.ycombinator.com

Post reply on HN
Print view View original

11–20 of 76 posts

Re: Launch HN: Traceloop (YC W23) – Detecting LLM Hallucinations with OpenTelemetry

#11

Post by nirga »

resiros wrote: post #4

Just wanted to say great work on standardizing otel for LLM applications ( https://github.com/open-telemetry/semantic-conventions/tree/... ] and opensourcing OpenLLMetry. We're also building in this space, focusing more on eval (agenta). I think using otel would make the whole space move much faster.

Thanks so much! I always say that I'm a strong believer in open protocols so I'd love to assist you if you want to use OpenLLMetry as your SDK. We onboarded other startups / competitors like Helicone and Honeyhive and it's been tremendously successful (hopefully that's what they'll tell you as well)

Re: Launch HN: Traceloop (YC W23) – Detecting LLM Hallucinations with OpenTelemetry

#12

Post by Lienetic »

Where can I learn more detail about the metrics you support and how they work?

I tried multiple other solutions but kept running into the problem that occasionally the framework would give me some score/evaluation of an LLM response that didn't make any sense, and there was minimal information about how it came up with the score. Often, I'd end up digging into the implementation of the framework to find the underlying evaluation prompt or classifier only to realize that the metric name is confusing or results are low confidence. I'm more cautious about using these tools now and look more deeply at how they work so that I can assess grading quality before relying on them to identify problematic outputs (e.g. hallucinations).

Re: Launch HN: Traceloop (YC W23) – Detecting LLM Hallucinations with OpenTelemetry

#13

Post by nirga »

swyx wrote: post #5

congrats on launch! the thing about OTel is that it is by nature vendor agnostic. so if i use OpenLLMetry, i should be able to pipe my otel traces to whatever existing o11y tool I use right? what is the benefit of a dedicated monitoring platform? (not cynical, just inviting you to explain more)

Great question and I see you already got a similar answer but I'll add some of my thoughts on this. We are actively promoting OpenLLMetry as a vendor agnostic way of observing LLMs (see some examples [1], [2]). We believe that people may start with whatever vendor they work with today and may gradually shift or use something like Traceloop because of specific features we have - for example the ability to take the raw data that we output with OpenLLMetry and add another layer of "smart metrics" (like qa relevancy, faithfulness, etc.) that we calculate on our backend / pipelines; or better tooling around observability of LLM calls, agents, etc.

[1] https://docs.newrelic.com/docs/opentelemetry/get-started/tra...

[2] https://docs.dynatrace.com/docs/observe-and-explore/dynatrac...

Re: Launch HN: Traceloop (YC W23) – Detecting LLM Hallucinations with OpenTelemetry

#14

Post by resiros »

Lienetic wrote: post #12

Where can I learn more detail about the metrics you support and how they work? I tried multiple other solutions but kept running into the problem that occasionally the framework would give me some score/evaluation of an LLM response that didn't make any sense, and there was minimal information about how it came up with the score. Often, I'd end up digging into the implementation of the framework to find the underlyin…

I think the issue is that many of these metrics (e.g. RAGAS) are LLM as a judge metrics. These are very far from reliable. Making them reliable is still a research problem. I've seen a couple of startups training their own LLM judge models to solve this problem. There are also some work to attempt to improve the reliability through sampling such as G-eval (https://github.com/nlpyang/geval).

One need to think of these metrics as a way to filter all the data to find potential issues, and not as a final evaluation criteria. The golden criteria should be human evaluators.

Re: Launch HN: Traceloop (YC W23) – Detecting LLM Hallucinations with OpenTelemetry

#15

Post by nirga »

swyx wrote: post #8
Oras wrote: post #2

Congratulations on launch. This is a crowded market, and there are many tools doing the same thing. How are you differentiating yourself from other tools like: Langfuse Portkey Keywords ai Promptfoo

not to mention langsmith? braintrust? humanloop? does that count? not sure what else - lets crowdsource a list here so that people can find them in future

I have it internally, I can share it if you want!

But to the point of comparison between these and tools like Traceloop - it's interesting to see this space and how each platform takes it's own path and finds its own use cases.

LangSmith works well within the LangChain ecosystem together with LangGraph, LangServe. But if you're using LlamaIndex, or even just vanilla OpenAI you'll be spending hours to set up your observability systems.

Braintrust and Humanloop (and to some extend other tools I saw in this area) take the path of "full development platform for LLMs".

We try to look at it as developers look at tools like Sentry. Continue working in your own IDE with your own tools (wanna manage your prompts in a DB or in git? Wanna use LLMs your own way with no frameworks? no problem). We install in your app, with one line and we work around your existing code base and make monitoring, evaluation and tracing work.

Re: Launch HN: Traceloop (YC W23) – Detecting LLM Hallucinations with OpenTelemetry

#16

Post by nirga »

BeautifulOrb wrote: post #6

there's a well known artist named traceloops who has a prolific/longstanding body of work. why did you choose this name?

I know! When we started every time I was googling "traceloop" this was the first result.

2 reasons why we chose it (in this order):

1. traceloop.com was available

2. we work with traces

Re: Launch HN: Traceloop (YC W23) – Detecting LLM Hallucinations with OpenTelemetry

#17

Post by nirga »

Lienetic wrote: post #12

Where can I learn more detail about the metrics you support and how they work? I tried multiple other solutions but kept running into the problem that occasionally the framework would give me some score/evaluation of an LLM response that didn't make any sense, and there was minimal information about how it came up with the score. Often, I'd end up digging into the implementation of the framework to find the underlyin…

We trained our own models for some of them, and we combined some well known NLP metrics (like Gruen [1]) to make this work.

You're right that it's hard to figure out how to "trust" these metrics. But you shouldn't look at them as a way to get an objective number about your app's performance. They're more of a way to detect deltas - regressions or changes in performance. When you get more alerts, or more negative results (or less alerts / less negative results) - you can tell you're improving. And this works for tools like RAGAS as well as our own metrics in my view.

[1] https://www.traceloop.com/blog/gruens-outstanding-performanc...

Re: Launch HN: Traceloop (YC W23) – Detecting LLM Hallucinations with OpenTelemetry

#18

Post by Lienetic »

resiros wrote: post #14
Lienetic wrote: post #12

Where can I learn more detail about the metrics you support and how they work? I tried multiple other solutions but kept running into the problem that occasionally the framework would give me some score/evaluation of an LLM response that didn't make any sense, and there was minimal information about how it came up with the score. Often, I'd end up digging into the implementation of the framework to find the underlyin…

I think the issue is that many of these metrics (e.g. RAGAS) are LLM as a judge metrics. These are very far from reliable. Making them reliable is still a research problem. I've seen a couple of startups training their own LLM judge models to solve this problem. There are also some work to attempt to improve the reliability through sampling such as G-eval ( https://github.com/nlpyang/geval ). One need to think of the…

Are there any approaches today that you've found are at least mostly reliable? Bonus points if it is somewhat clear/easy/predictable to know when it isn't or won't be.

We use human evaluation but that is naturally far from scalable, which has especially been a problem when working on more complicated workflows/chains where changes can have a cascading effect. I've been encouraging a lot of dev experimentation on my team but would like to get a more consistent eval approach so we can evaluate and discuss changes with more grounded results. If all of these metrics are low confidence, they become counterproductive since people easily fall into the trap of optimizing the metric.

Re: Launch HN: Traceloop (YC W23) – Detecting LLM Hallucinations with OpenTelemetry

#19

Post by nirga »

Lienetic wrote: post #18
resiros wrote: post #14

Earlier quoted context omitted.

I think the issue is that many of these metrics (e.g. RAGAS) are LLM as a judge metrics. These are very far from reliable. Making them reliable is still a research problem. I've seen a couple of startups training their own LLM judge models to solve this problem. There are also some work to attempt to improve the reliability through sampling such as G-eval ( https://github.com/nlpyang/geval ). One need to think of the…

Are there any approaches today that you've found are at least mostly reliable? Bonus points if it is somewhat clear/easy/predictable to know when it isn't or won't be. We use human evaluation but that is naturally far from scalable, which has especially been a problem when working on more complicated workflows/chains where changes can have a cascading effect. I've been encouraging a lot of dev experimentation on my t…

I tend to find classic NLP metric more predictable and stable than "LLM as a judge" metrics so I'd try to see if you rely on them more.

We've written a couple of blog posts about some of them: https://www.traceloop.com/blog

Re: Launch HN: Traceloop (YC W23) – Detecting LLM Hallucinations with OpenTelemetry

#20

Post by Lienetic »

nirga wrote: post #15
swyx wrote: post #8

Earlier quoted context omitted.

not to mention langsmith? braintrust? humanloop? does that count? not sure what else - lets crowdsource a list here so that people can find them in future

I have it internally, I can share it if you want! But to the point of comparison between these and tools like Traceloop - it's interesting to see this space and how each platform takes it's own path and finds its own use cases. LangSmith works well within the LangChain ecosystem together with LangGraph, LangServe. But if you're using LlamaIndex, or even just vanilla OpenAI you'll be spending hours to set up your obse…

I'd love to see that list!
Post reply on HN