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

41–50 of 76 posts

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

#41

Post by threeseed »

mshcodez wrote: post #28
nirga wrote: post #11

Earlier quoted context omitted.

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)

HoneyHive founder here. Nir and team have built an amazing OSS package and have been fantastic to collaborate with (despite being competitors)! As an industry, I think more of us need to work together to standardize telemetry protocols, schemas, naming conventions, etc. since it’s currently all over the place and leads to a ton of confusion and headache for developers (which ultimately goes against the whole point of…

Your startup is as deceptive as Traceloop.

You make claims like "detect LLM errors like hallucination" even though you have no guaranteed ability to do this.

At best you can assist in detection.

As someone who works at a large enterprise deploying LLMs I can tell you many people are getting pretty tired of the false claims.

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

#42

Post by nirga »

threeseed wrote: post #41
mshcodez wrote: post #28

Earlier quoted context omitted.

HoneyHive founder here. Nir and team have built an amazing OSS package and have been fantastic to collaborate with (despite being competitors)! As an industry, I think more of us need to work together to standardize telemetry protocols, schemas, naming conventions, etc. since it’s currently all over the place and leads to a ton of confusion and headache for developers (which ultimately goes against the whole point of…

Your startup is as deceptive as Traceloop. You make claims like "detect LLM errors like hallucination" even though you have no guaranteed ability to do this. At best you can assist in detection. As someone who works at a large enterprise deploying LLMs I can tell you many people are getting pretty tired of the false claims.

I replied to you in a different thread, I don't think calling our companies "deceptive" will help you or me get anywhere. While I agree with you that detection will never be hermetic, I don't think this is the goal. By design you'll have hallucinations and the question should be how can you monitor the rate and look for changes and anomalies.

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

#44

Post by its_ethan »

xyst wrote: post #34
remram wrote: post #31

Acknowledging that AI is unreliable, the solution is to layer another AI to hopefully let you know about it. Of course, brilliant, why did I expect anything different from the AI industry.

?? but who is monitoring the AI layer monitoring the AI who produced the original output ?? openai audited by claudeai which is then audited by gemini ai... then to close the loop, gemini ai is then audited by openai

I had read the OP's comment as sarcastic, but you never know these days lol

Your concern would be exactly mine as well, and why I assumed "brilliant" was sarcasm, cause it feels like handing over the problem to the same solution that got you the problem in the first place?

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

#45

Post by nirga »

its_ethan wrote: post #44
xyst wrote: post #34

Earlier quoted context omitted.

?? but who is monitoring the AI layer monitoring the AI who produced the original output ?? openai audited by claudeai which is then audited by gemini ai... then to close the loop, gemini ai is then audited by openai

I had read the OP's comment as sarcastic, but you never know these days lol Your concern would be exactly mine as well, and why I assumed "brilliant" was sarcasm, cause it feels like handing over the problem to the same solution that got you the problem in the first place?

It has the same logic of saying you dont want to use a computer to monitor or test your code since it will mean that a computer will monitor a computer. AI is a broad term, I agree you can use GPT (or any LLM) to grade an LLM in an accurate way but that’s not the only way you can monitor.

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

#46

Post by its_ethan »

nirga wrote: post #45
its_ethan wrote: post #44

Earlier quoted context omitted.

I had read the OP's comment as sarcastic, but you never know these days lol Your concern would be exactly mine as well, and why I assumed "brilliant" was sarcasm, cause it feels like handing over the problem to the same solution that got you the problem in the first place?

It has the same logic of saying you dont want to use a computer to monitor or test your code since it will mean that a computer will monitor a computer. AI is a broad term, I agree you can use GPT (or any LLM) to grade an LLM in an accurate way but that’s not the only way you can monitor.

> computer to monitor or test your code since it will mean that a computer will monitor a computer

I mean... you don't trust the computer in that case, you trust the person who wrote the test code. Computers do what they're told to do, so there's no trust required of the computer itself. If you swap out the person (that you're trusting) writing that code with an AI writing that test code, then it's closer to your analogy - and in that case, I (and the guy above me, it seems) wouldn't trust for anything impactful.

Even if you're not using an LLM specifically (which no one in this chain even said you were), an AI built off some training set to eliminate hallucinations is still just an AI. So you're still using an AI to keep an AI in check, which begs the question (posed above) of: what keeps your AI in check?

Poking fun at a chain of AI's all keeping each other in check isn't really a dig at you or your company. It's more of a comment on the current industry moment.

Best of luck to you in your endeavor anyway, by the way!

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

#47

Post by cmcconomy »

bionhoward wrote: post #26

Check out these Wikipedia articles: Confabulation https://en.m.wikipedia.org/wiki/Confabulation Hallucination https://en.m.wikipedia.org/wiki/Hallucination What drove the AI industry to blow off accepted naming from psychopathology and use the word for PERCEPTUAL errors to refer to LANGUAGE OUTPUT errors? When AI hallucinates, and AI people already use the preferred term “hallucination” to label confabulations, then…

if i may theorize: one of these two terms is generally recognised by the broader english speaking community

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

#48

Post by nirga »

its_ethan wrote: post #46
nirga wrote: post #45

Earlier quoted context omitted.

It has the same logic of saying you dont want to use a computer to monitor or test your code since it will mean that a computer will monitor a computer. AI is a broad term, I agree you can use GPT (or any LLM) to grade an LLM in an accurate way but that’s not the only way you can monitor.

> computer to monitor or test your code since it will mean that a computer will monitor a computer I mean... you don't trust the computer in that case, you trust the person who wrote the test code. Computers do what they're told to do, so there's no trust required of the computer itself. If you swap out the person (that you're trusting) writing that code with an AI writing that test code, then it's closer to your ana…

Thanks! I wasn’t offended or anything, don’t get the wrong impression.

What strikes me odd is the fact that an AI that checks AI is an issue. Because AI can mean a lot of things - from a encoder architecture, a neural network, or a simple regression function. And at the end of the day, similar to what you said - there was a human building and fine tuning that AI.

Anyway, this feels more of a philosophical question than an engineering one.

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

#49

Post by lukan »

mshcodez wrote: post #28
nirga wrote: post #11

Earlier quoted context omitted.

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)

HoneyHive founder here. Nir and team have built an amazing OSS package and have been fantastic to collaborate with (despite being competitors)! As an industry, I think more of us need to work together to standardize telemetry protocols, schemas, naming conventions, etc. since it’s currently all over the place and leads to a ton of confusion and headache for developers (which ultimately goes against the whole point of…

No idea how honest this is (I might have gotten a bit cynical) - but reading this sounds like you guys have a really healthy constructive competition with elements of cooperation! Love to see that.

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

#50

Post by nonameiguess »

This is poorly worded. Detecting "hallucinations" as the term is commonly used, as in a model making up answers not actually in its source text, or answers that are generally untrue, is fundamentally impossible. Verifying the truth of a statement requires empirical investigation. It isn't a feature of language itself. This is just the basic analytic/synthetic distinction identified by Kant centuries ago. It's why we have science in the first place and don't generate new knowledge by reading and learning to make convincing sounding arguments.

Your far more scaled-down claim, however, that you can detect answers that don't address a prompt at all, or make claims when summarizing known other text that isn't actually in the original text, is definitely doable, but raises a maybe naive or stupid question. If you can do this, why not sell an LLM that simply doesn't do these stupid things in the first place? Or why do the people currently selling LLMs not just automatically detect obvious errors and not make them? Doesn't your business as constituted depend upon LLM vendors never figuring out how to do this themselves?

Post reply on HN