Nearly half of Gen Z workers say they get better job advice from ChatGPT than their managers, according to a recent survey.

Many Gen Z employees say ChatGPT is giving better career advice than their bosses::Nearly half of Gen Z workers say they get better job advice from ChatGPT than their managers, according to a recent survey.

  • kromem@lemmy.worldEnglish
    01·
    11 months ago

    There’s something to be said for the abilities of a tool reflecting its wielder.

    In research circles, the most advanced pipelines in terms of prompting have a 90% success rate at things the same model only gets right around 30% of the time with naive zero shot prompting.

    At a minimum, people should be familiar with chain of thought prompting if using the models. That one is very easy to incorporate and makes a huge difference on complex problems.

    Though for anyone actually building serious pipelines for these products, the best technique I’ve seen to date was this one from DeepMind:

    We introduce SELF-DISCOVER, a general framework for LLMs to self-discover the task-intrinsic reasoning structures to tackle complex reasoning problems that are challenging for typical prompting methods. Core to the framework is a self-discovery process where LLMs select multiple atomic reasoning modules such as critical thinking and step-by-step thinking, and compose them into an explicit reasoning structure for LLMs to follow during decoding. SELF-DISCOVER substantially improves GPT-4 and PaLM 2’s performance on challenging reasoning benchmarks such as BigBench-Hard, grounded agent reasoning, and MATH, by as much as 32% compared to Chain of Thought (CoT). Furthermore, SELF-DISCOVER outperforms inference-intensive methods such as CoT-Self-Consistency by more than 20%, while requiring 10-40x fewer inference compute. Finally, we show that the self-discovered reasoning structures are universally applicable across model families: from PaLM 2-L to GPT-4, and from GPT-4 to Llama2, and share commonalities with human reasoning patterns.

    So yes, maybe you aren’t getting a lot out of the models. But a lot of people are, and the difference between your experiences and theirs may just boil down to experience in using the tool. If I just started using Photoshop for an hour or two I might complain about how the software sucks at making good looking images. But we both know it wouldn’t be the software’s fault.

    • Rikudou_Sage@lemmings.worldEnglish
      1·
      11 months ago

      Well, one more comment like that and I guess I’m gonna have to edit my original comment, because I don’t want to explain again. I’m getting quite a lot out of LLMs (GPT-4, to be specific), it’s just that they’re very stupid. When they don’t straight up lie, they don’t know stuff. It’s quite simple, really, I usually deal with very complex problems that few people dealt with, the AI has (close to) no data on that, so it runs in circles and is not able to help.

      But when presented with questions that it has training data on, it’s brilliant - recently I needed to use reflection to get all types implementing an interface in .NET with the caveat that the interface is generic. GPT-4 was able to solve that problem 3rd message in the conversation, while I’m pretty sure it would take me hours, because I’d need to learn a lot of .NET’s internal workings before arriving at the quite simple solution.

      So, a good career advice - which one do you feel like it is? A simple question with a straight correct solution, or a complex and nuanced issue where there isn’t one general truth? Because the only correct answer to a request for career advice by someone who doesn’t know your situation extensively is (a version of) “I don’t know, what’s your situation in detail?”. Knowing GPT, it didn’t ask that question.

      So yes, LLMs are great! Just learn which use-cases it excels at and don’t ask it for complex advice.