Just after takeoff is the worst time to have a problem. Hopefully they had the minimum crew. Also hopefully it wasn't carrying a nuke and/or it wasn't compromised.
also the context window sizes are too low. I can't operate in 65,000 windows any more because even just reading the code's file structure overruns it and gets me nowhere. Definitely its own art form.
200k context windows and above for me now
I saw a paper last night that should help this a lot though
I get that it's a deal breaker to some; it definitely requires patience.
In Pi, /new is my best friend and most-used command for sure. For simple tasks (I decompose complex ones anyway since I don't trust small local LLMs to do this for me), the model doesn't need much context, given that I'm proficient in my codebase myself: "I'd like Feature X. Look into files 1, 2 and 3 to make your edits."
no, most won’t burn themselves by publicly linking them as vibe coded
there is that ny times article about the peptide guy and lovable showcase by revenue though. I guess next up are even more disqualifiers about the term “successful”, but my outstanding question is who cares? What does convincing you buy, an Anthropic pro subscription at best?
last time I waded into this discussion with my own examples, the "billionaires exploit people" maximalists kept moving the goal post indefinitely
I had asked "what about a fund manager earning the carry"
management fee and performance fee, employees not entirely necessary.
the main result was a brief back and forth to understand that role, because this class of people are completely separated from all the exceptions that break their argument, and then a brief moment of acceptance, before focusing on the prevalence of this kind of billionaire amongst all billionaires. Which I thought was funny because there are not many billionaires to begin with. 20 fund managers on the list would be a large percentage of billionaires.
The allegation here is that it's not actually a fine-tune of Qwen, but instead an undisclosed mashup (merge) of someone else's fine-tune of Qwen and the original model. Rio subsequently said that the model was in fact a merge, that they did additional fine-tuning after the merge, and that they accidentally uploaded the base merge instead of the version with additional fine-tuning. But this seems like quite an oversight...
reply