I just started a new job. A mix of JS, WASM (C++) and Python. It's been a blessing to help understand and explain an unfamiliar codebase to me. Sometimes the analysis isn't deep enough but I've been able to create enough guiding documents to get it right most of the way through, and for the rest I can continue and dive deeper on my own with further prompting.
I've started using it to write some code, which I then use further prompting to review before my own final review. I feel a lot more productive, I can focus on high level ideas and not think about tiny implementation details.
Having instrumentation code magically created in minutes and being able to validate assumptions before/after making changes by doing manual testing and feeding AI logs has been a great use for me - this kind of stuff is boring and would kill my motivation and productivity in the past. AI helps here so I can move on to the fun stuff, helps me stay engaged and interested.
It's great for writing unit tests and doing log analysis. The usual AI pitfalls apply like going into loops that lead nowhere and hallucinating things, but I've gotten better at spotting it and steering it away. I try not to take what it gives me at face value and use follow up prompts to challenge assumptions or verify things.
So overall, it's been an immense help for me. I've got some interesting projects coming up that are more greenfield work, we'll see if this holds up compared to an existing codebase.
I bought a Creality Ender 3 V2 a little over a year ago, spent 6 months printing things and fiddling with it and finally had it with how primitive it is.
If you have the time and patience for tinkering, the Voron is great.
I built a Voron 2.4 and Voron Trident this year. Both printers are designed with automatic bed leveling as a base feature and I modded them right from the start to have automatic z offset calculation as well with a fancy probe. With these 2 features I have print it and forget it operation 99% of the time with no issues. There have also been some open source multi filament/material projects that you can add to the printers since you have full control of the hardware and software.
I actually got a 10% raise which management was all to happy to say was the best thing they had ever done for a single person. The problem is 10% is nothing if your base pay to begin with was 50% below market rate.
I left a job a few years ago and put the entire management on blast because they could not fathom the singular reason for leaving was poor compensation.
A few months later some former coworkers told me that everyone in the company got a surprise raise a few weeks after I left.
I've started using it to write some code, which I then use further prompting to review before my own final review. I feel a lot more productive, I can focus on high level ideas and not think about tiny implementation details.
Having instrumentation code magically created in minutes and being able to validate assumptions before/after making changes by doing manual testing and feeding AI logs has been a great use for me - this kind of stuff is boring and would kill my motivation and productivity in the past. AI helps here so I can move on to the fun stuff, helps me stay engaged and interested.
It's great for writing unit tests and doing log analysis. The usual AI pitfalls apply like going into loops that lead nowhere and hallucinating things, but I've gotten better at spotting it and steering it away. I try not to take what it gives me at face value and use follow up prompts to challenge assumptions or verify things.
So overall, it's been an immense help for me. I've got some interesting projects coming up that are more greenfield work, we'll see if this holds up compared to an existing codebase.