What is the maximum context size in the web UI?
Learning to Reason with LLMs
461–470 of 1001 posts
Re: Learning to Reason with LLMs
#462Reading through the Chain of Thought for the provided Cipher example (go to the example, click "Show Chain of Thought") is kind of crazy...it literally spells out every thinking step that someone would go through mentally in their head to figure out the cipher (even useless ones like "Hmm"!). It really seems like slowing down and writing down the logic it's using and reasoning over that makes it better at logic, simi…
Seriously. I actually feel as impressed by the chain of thought, as I was when ChatGPT first came out. This isn't "just" autocompletion anymore, this is actual step-by-step reasoning full of ideas and dead ends and refinement, just like humans do when solving problems. Even if it is still ultimately being powered by "autocompletion". But then it makes me wonder about human reasoning, and what if it's similar? Just fo…
I think it's similar, although I think it would be more similar if the LLM did the steps in lower layers (not in English), and instead of the end being fed to the start, there would be a big mess of cycles throughout the neural net.
That could be more efficient since the cycles are much smaller, but harder to train.
Re: Learning to Reason with LLMs
#463This is incredible. In April I used the standard GPT-4 model via ChatGPT to help me reverse engineer the binary bluetooth protocol used by my kitchen fan to integrate it into Home Assistant. It was helpful in a rubber duck way, but could not determine the pattern used to transmit the remaining runtime of the fan in a certain mode. Initial prompt here [0] I pasted the same prompt into o1-preview and o1-mini and both c…
Isn't there a big "Share" button at the top right of the chatgpt interface? Or are you using another front end?
In ChatGPT for Business it limits sharing among users in my org, without an option for public sharing.
Re: Learning to Reason with LLMs
#464Aren't LLMs much more limited on the amount of output tokens than input tokens? For example, GPT-4o seems to support only up to 16 K output tokens. I'm not completely sure what the reason is, but I wonder how that interacts with Chain-of-Thought reasoning.
Re: Learning to Reason with LLMs
#465This is incredible. In April I used the standard GPT-4 model via ChatGPT to help me reverse engineer the binary bluetooth protocol used by my kitchen fan to integrate it into Home Assistant. It was helpful in a rubber duck way, but could not determine the pattern used to transmit the remaining runtime of the fan in a certain mode. Initial prompt here [0] I pasted the same prompt into o1-preview and o1-mini and both c…
Did you edit the message? I cannot see anything now in the screenshot, too low resolution
Re: Learning to Reason with LLMs
#466Student here. Can someone give me one reason why I should continue in software engineering that isn't denial and hopium?
Coding is going to be mediated by these LLMs everywhere — you’re right about that. However, as of today, and for some time, practitioners will be critical partners / overseers; what this looks like today in my workflow is debugging, product specification, coding the ‘hard bits’, reworking / specifying architectures. Whatever of these fall of the plate in the coming years, you’ll never lose your creative agency or determination of what you want to build, no matter how advanced the computers. Maybe give Iain Banks a read for a positive future that has happy humans and super-intelligent AI.
We have working fine cabinet makers who use mostly hand tools and bandsaws in our economy, we have CAD/CAM specialists who tell CnC machines what to build at scale; we’ll have the equivalent in tech for a long time.
That said, if you don’t love the building itself, maybe it’s not a good fit for you. If you do love making (digital) things, you’re looking at a super bright future.
Re: Learning to Reason with LLMs
#467Student here. Can someone give me one reason why I should continue in software engineering that isn't denial and hopium?
Don't do it, help us keep our high salaries :D Joking aside, even with AI generating code, someone has to know how to talk to it, how to understand the output, and know what to do with it. AI is also not great for novel concepts and may not fully get what's happening when a bug occurs. Remember, it's just a tool at the end of the day.
just change this to "I have AI Skills!!" :)
Re: Learning to Reason with LLMs
#468Earlier quoted context omitted.
Software engineering contains a lot more than just writing code. If we somehow get AGI, it'll change everything, not just SWE. If not, my belief is that there will be a lot more demand for good SWEs to harness the power of LLMs, not less. Use them to get better at it faster.
This thing is doing planning and ascending the task management ladder. It's not just spitting out code anymore.
AI Automated planning and action are an old (45+ year) field in AI with a rich history and a lot of successes. Another breakthrough in this area isn't going to eliminate engineering as a profession. The problem space is much bigger than what AI can tackle alone, it helps with emancipation for the humans that know how to include it in their workflows.
Re: Learning to Reason with LLMs
#469Student here. Can someone give me one reason why I should continue in software engineering that isn't denial and hopium?
Software lets you take pretty much anyone else’s job and do it better.
Re: Learning to Reason with LLMs
#470Earlier quoted context omitted.
Software engineering contains a lot more than just writing code. If we somehow get AGI, it'll change everything, not just SWE. If not, my belief is that there will be a lot more demand for good SWEs to harness the power of LLMs, not less. Use them to get better at it faster.
This thing is doing planning and ascending the task management ladder. It's not just spitting out code anymore.
Yes, and they will get better. Billions are being poured into them to improve.
Yet I'm comparing these to the problems I solve every day and I don't see any plausible way they can replace me. But I'm using them for tasks that would have required me to hire a junior.
Make that what you will.