Can this guy, or someone else post a full days (4-8 hours, or what ever is spent in the weeds) stream of work to youtube or something. I just want to watch the process to see what I'm missing. Or if there is anyone that already does that can they recommend it to me. I would appreciate it.
Got through about 45 min at 2x speed / some skipping ahead out of pure fascination. Man that's something else. It's like bug-driven-development. Get the LLM to churn out a huge chunk of text, then skim the code for about 10 seconds and say it looks good. Then spend a while testing and hitting one error after the next until it finally seems to work. Repeat.
Keep in mind that in their mind they are performing very well as they (or rather Claude) are churning PR after PR.
We gotta stop the endless characters production at least for a bit so we and the git servers get some time to breathe free from slop. A tactical coffee spill is a small price to pay.
Are you saying that because you're also skeptical? I haven't had the best time switching to agent coding. I mean for throwaway work its fine but its kind of boring and aider still messes up from time to time
I probably lean on the sceptical side of the spectrum. I'm not against giving it a go if I can get value out of it but I'm not having the wonderful experience that these people are having.
- The asynchronous nature of it slows me down and it feels the opposite of what this bloke is saying around getting into a flow.
- I miss things because I'm not thinking it all the way through.
- The issues with errors or hallucinations.
- It does not feel faster (I might blow through a couple of things really fast, but the issues created elsewhere sometimes eat all that saved time up).
- The quality of work is all over the shop. Bigger projects just fall apart after a while.
I also wonder if the way I think is hindering me. I don't like natural language. I struggle to communicate at the best of times. All my emails are dot points. If someone asks me for a diagram I write it in plantuml or using a python library. I work in DevOps and love declarative manifests and templates.
Try as an initial step having the agentic AI improve your prompt for you. I have a "prompt improvement prompt template", which is a standardized document (customized for each project I'm working on), that has a bunch of boilerplate instructions in it, along with a section where I paste in my first-draft prompt. I then feed this document (boilerplate + crappy prompt) into the AI and it creates a way better prompt for me. Then I edit that to ensure it's correct, and then that becomes the prompt I use.
An oracle was expected because that's what everyone kept saying it was or would be. If LLMs were shown and demonstrated realistically people would think they were really neat and find ways to use them. Instead I'm told I have phd™ level intelligence in my pocket. So of course people are going to be mad when it gets stumped on problems my 4yo could figure out.
I worry things will be lost in translation (maybe would have already), Or the LLMs will fill in the gaps with wrong information, like some sort of weird telephone game.
That said, I have one ESL on my team who uses LLMs a lot like that and it's fine so who knows.
My experience has been interesting. I have been sending super short, mostly dot point emails since before LLMS. Pre ChatGPT I used to cop a bit of shit about it. Now thought, people love it.
People have bought snake oil since the dawn of time. People have blindly followed diet/medical/lifestyle influencers since long before the internet. It's not going away. I'm sure you have seen some plum on the internet say "Let food be thy medicine" before.
I recall seeing a couple of blog posts lately about docker swarm and how its better now. I can see a few references to it in the latest release notes so I guess it's still getting some love.
It didn't seem to do anything well. And weird quotes like 'I think it one-shotted that too' on something important. What on earth is this. Reading it is like experiencing a bad weird dream.
For phones. If you use the YT app (Or logged in I think). If you disable your watch history it removes the shorts. But I wish there was another way. I use Unhook browser plugin on my computer browser.
reply