A friend of mine, a dermatologist, told me that LLMs are quite performant for melanoma analysis. Based on their own statistics, LLMs are able to beat humans with ~10 years of experience in the field.
They will never beat the human instinct tho, but they can be great tools sometimes. Unfortunately, LLMs mostly produce garbage.
>Really? Lol. If it's true why would you publish it? To ensure Microsoft will patch it up and fuck up your workflow?
It's true and it's their official pricing, so talking about it won't change anything.
People are spending way too much money with Claude Code while they could simply pay for GitHub Copilot and fire up OpenCode to get the same results but way cheaper.
> I am not seeing the performance degradation everyone talks about after 50% context window.
I pretty much agree with that. I use long sessions and stopped trying to optimize the context size, the compaction happens but the plan keeps the details and it works for me.
I've been searching for a solution to let my wife have access to my master password if I die someday. This is definitely something that could work, thank you!
I've ditched RSS feeds more than 10 years ago but I'm increasingly wanting to go back to them. Thank you for sharing this blog post, it'll help to get me started.
I didn't know who he is and still found this blog post really interesting because the real topic is about marketing your app when you're a software developer.
They will never beat the human instinct tho, but they can be great tools sometimes. Unfortunately, LLMs mostly produce garbage.