I think it’s dishonest to use a paying client as a test subject for fundamental functionality they pay for, without their prior consent.
Please do not A/B test my workflow
151–160 of 225 posts
Re: Please do not A/B test my workflow
#152Earlier quoted context omitted.
> I don't believe A/B testing is an inherent evil, you need to get the test design right, and that would be better framing for the post imo. I disagree in the case of LLMs. AI already has a massive problem in reproducibility and reliability, and AI firms gleefully kick this problem down to the users. "Never trust it's output". It's already enough of a pain in the ass to constrain these systems without the companies s…
I think you would be hard pushed to find any big tech company which doesn't do some kind of A B testing. It's pretty much required if you want to build a great product.
A responsible company develops an informed user group they can test new changes with and receive direct feedback they can take action on.
Re: Please do not A/B test my workflow
#153The framing of A/B testing as a "silent experimentation on users" and invoking Meta is a little much. I don't believe A/B testing is an inherent evil, you need to get the test design right, and that would be better framing for the post imo. That being said, vastly reducing an LLMs effectiveness as part of an A/B test isn't acceptable which appears to be the case here.
I apologize for doing this - and I agree. I will revise
I still think you have a point here. Doing this kind of testing on users unwittingly is unethical in my opinion
Re: Please do not A/B test my workflow
#154Earlier quoted context omitted.
There's a difference between "LLMs are inherently black boxes that require lots of work to attempt to understand" and explicitly changing how a piece of software works. Should people not complain about unannounced changes to the contents of their food or medicine because we don't understand everything about how the human body works?
Except the system prompt that gets prepended to your own prompt is part of the black box, and obviously should be expected to change over time. You are also told that you're not allowed to reverse engineer it. Even in the absence of the system prompt being changed, the output of the LLM is non-deterministic. I'm not sure I understand your last analogy. How would changes to the human body change the contents of the fo…
I think we're getting lost in the weeds. This has almost nothing to do with the LLM. It's about A/B testing. There's a piece of software where the behavior is being changed in unannounced and unexpected ways, at least as far as the author is concerned. The same criticism could apply to any other "workflow" or "professional" software.
There's some added flavor because the LLM is indeed non-deterministic, which could make it harder to realize that a change in behavior is caused by a change in the software, not randomness from the LLM. But there is also lots of software that deals with non-deterministic things that aren't LLMs, e.g. networks, physical sensors, scientific experiments, etc. Am I getting more timeouts because something is going on in my network or because some software I use is A/B testing some change?
Re: Please do not A/B test my workflow
#155Earlier quoted context omitted.
> vibe coded Claude code cli releases are a buggy mess too this is what gets me. are they out of money? are so desperate to penny pinch that they can't just do it properly? what's going on in this industry?
I’m a huge user of AI coding tools but I feel like there has been some kind of a zeitgeist shift in what is acceptable to release across the industry. Obviously it’s a time of incredibly rapid change and competition, but man there is some absolute garbage coming out of companies that I’d expect could do better without much effort. I find myself asking, like, did anyone even do 5 minutes of QA on this thing?? How has…
I mean it's like, really they don't even need agentic AI or whatever, they could literally just employ devs and it wouldn't make a difference
like, they'll drop $100 billion on compute, but when it comes to devs who make their products, all of a sudden they must desperately cut costs and hire as little as possible
to me it makes no sense from a business perspective. Same with Google, e.g. YouTube is utterly broken, slow and laggy, but I guess because you're forced to use it, it doesn't matter. But still, if you have these huge money stockpiles, why not deploy it to improve things? It wouldn't matter anyways, it's only upside
Re: Please do not A/B test my workflow
#156Earlier quoted context omitted.
fuck man, I'm either seriously stupid or y'all are taking crazy pills. LLMs are auto-complete on steroids; I've lived through enough iterations of Markov Chains giving semi-sensible output (that we give meaning to) and neural networks which present the illusion of intelligence to see directly what these LLMs are: a fuck load of compute designed to find "the next most common word" given the preceding 10,000 or more wo…
This message contains a lot of emotions and not too many coherent arguments. What did you actually want to say?
If you seek to audit code through the use of LLMs then you have inherently misunderstood the capabilities of the technology and will be left disappointed.
Re: Please do not A/B test my workflow
#157Re: Please do not A/B test my workflow
#158Earlier quoted context omitted.
> People don’t enjoy the thought of auditing code… someone else will do it I think that with modern LLMs auditing a big project personally, instead of relying on someone else to do it, actually became more realistic. You can ask an LLM to walk you through the code, highlight parts that seem unusual or suspicious, etc. On the other hand, LLMs also made producing code cheaper then ever, so you can argue, that big proje…
fuck man, I'm either seriously stupid or y'all are taking crazy pills. LLMs are auto-complete on steroids; I've lived through enough iterations of Markov Chains giving semi-sensible output (that we give meaning to) and neural networks which present the illusion of intelligence to see directly what these LLMs are: a fuck load of compute designed to find "the next most common word" given the preceding 10,000 or more wo…
I wish people would move on from this mindset. "Agentic" workflows such as those implemented by Claude Code or Cursor can definitely reason about code, and I've used them to successfully debug small issues occurring in my codebase.
We could argue about how they only "predict the next word", but there's also other stuff going on in the other layers of their NNs which do facilitate some sort of reasoning in the latent space.
Re: Please do not A/B test my workflow
#159Earlier quoted context omitted.
Maybe then, it's just my expectation of what they would be doing. What else is all the telemetry for? As a side note, my impression is that this is less of a photoshop and more of a website situation in that most of the functionality is input and response to/from their servers.
Telemetry is, ideally, collected with the intention of improving software, but that doesn't necessitate doing live A/B tests. A typical example: report hardware specs whenever the software crashes. Use that to identify some model of GPU or driver version that is incompatible with your software and figure out why. Ship a fix in the next update. What you don't do with telemetry is randomly do live experiments on your u…
Telemetry is “ideally” this. What makes you think other hosted llms (grok/xAI) don’t do this?
You also got the information from asking Claude questions about its prompt, maybe it hallucinated this?
Re: Please do not A/B test my workflow
#160A professional tool is something that provides reliable and replicable results, LLMs offer none of this, and A/B testing is just further proof.
That’s not a problem of LLMs but of using services provided by others.
How often were features changed or deactivated by cloud services?