Personally I use gh copilot in vscode and make new worktrees when I want parallel agents that are both going to write code.
For research, planning, figuring out bugs, etc I usually don’t bother creating the worktree until I’ve decided on the implementation.
I’m sure there’s better workflows and software, but all I’ve got for work is gh copilot and Claude enterprise. I like copilot better than Claude for the most part.
I had a totally benign chat with OpenAI and it titled it as “amateur porn” in Chinese characters, it was very alarmed when I pointed the conversation name out to it. It almost never misses these days, but when it does the failure modes are very strange.
I remember getting a bunch of „Thanks for watching! Subscribe and smash that like button“ in the middle of chat sessions a few times (like, more than 3 times over the past 3y)
It kind of makes sense when you think about it. If the training data is YouTube transcripts, people often abruptly switch from content to asking for a subscription.
We're all training similarly large base++; near same data, just pricing it differently... with grok removing a few filters and maybe some safeguards? For that matter, many of the benchmarks are flawed and are just easily gamed and whatnot. iykyk.
Very cool and what an amazing way to learn so much beyond what you do in those years at university (at least in the engineering sense). I wish we had software and hardware open to be able to run custom setups whether its NVIDIA on x64 or Ampere/arm64 with MacOS.
Considering Musk's power and the shrinking moat of OpenAI you would think he would be create something better with government support - or as some new department.
