We’ve ultimately decided to treat the models with more respect, nurturing, and collaborative support than we ever did our follow human keyboard smashers. Writing all the documentation, detailed guidance, allowing them multiple attempts, to help the LLMs be successful. But Brenda, the early in career new grad? “please read this poorly written, 5 year-old, incomplete wiki, and don’t ask me questions”
I’ve been thinking about this for months, and still don’t know what to make of it.
Respect (or lack thereof) goes both ways: both the writer and reader. I have frequently felt disrespected by producing documentation, planning/etc that isn't read. In the end I mostly rely on oral transmission of knowledge because then at least I can read the room and know if I'm providing some value to people, and ultimately we're both trapped in the room together and have to invest the same amount of time.
The LLM isn't always smart, but it's always attentive. It rewards that effort in a way that people frequently don't. (Arguably this is a company culture issue, but it's also a widespread issue.)
Great framing of the problem. I do think it's a culture issue with "Agile" practices in particular - By design, there is no time budgeted for reading, writing, reflection, or discussion. Sprint, sprint, sprint.
In organizations that value innovation, people will spend time reading and writing. It's a positive feedback loop, almost a litmus test of quality of the work culture.
I would also be motivated to write better documentation if I had a junior dev sitting right next to me, utterly incapable of doing any work unless I document how; but also instantly acting on documentation I produce, and giving me rapid feedback on which parts of the documentation are sending the wrong message.
How can an LLM “talk” to another LLM, except by emitting tokens in its output stream?
You can name the mechanism whatever you want, but the models don’t have hands. Tool calling conventions (as a concept, or as a spec) is what gives the model hands!
Hard Drive, ostensibly about Bill Gates, was a great read when I was a kid. I recommend ‘Microserfs’ from Douglas Coupland as a fictional (but grounded) homage to the work in the 90s.
This is a build or test lab, not the offices of developers. I visited multiple times in the period mentioned for the picture, and saw multiple of these. The one I saw most often was the NT build lab. When I started there in the mid-2000s, these labs were still used, although the build labs were a little less densely packed thanks to remote tools.
A post I wrote thinking about the 'addiction' that ads & subscription revenue can cause, and how it leads to a loss of identity in companies whose core products were not 'recurring revenue' originally. (e.g., contrast Google / Meta to Microsoft / Apple / Oracle).
Gonna save this post for some arbitrary point in the future to pull out as a point against ‘impossible’. Might have to gift it to my descendants to make sure it’s available for long enough… /s
