A useful technique to experiment with if you care about token counts is asking the LLM to shorten the prompt in a meaning-preserving way. (Experiment. Results, like all LLM results, are varied). I don't think I've seen it in the comments yet, apologies if it's a duplicate.
As an example, I've taken the prompt Neil shared and shortened it - transcript: https://chatgpt.com/share/683b230e-0e28-800b-8e01-823a72bd004b
1.5k words/2k tokens down to 350 tokens. It seems to produce reasonably similar results to the original, though Neil might be a better judge of that. I'd have tried it on my own prompt, but I've long found that the value I derive from system prompts is limited for what I do. (Not impugning Croissanthology here - merely a facet of how my brain works)
Having been at the same conference: The gap was staggering. On the one side, people & teams who by now have deeply agentic workflows (not just code - individualized workflows across the board were a thing). In the middle serious discussions on rather useless things like "LOC isn't a good productivity metric, how do we count productivity now". And a large chunk just very disconnected from what is and isn't possible, in both directions.
Even if we're at the top of the S curve (personal take: Probably, at least without fundamental breakthroughs beyond "scale"), there's massive changes already deeply baked in, and for the unaware teams, it will feel like continued exponential growth just because understanding is slowly trickling down.
The - I think - most realistic take was Bill Coughran comparing it to the dot com boom, the fact that there were a lot of dead bodies left on the ground after that, and that a few well-positioned companies experienced tremendous growth after.
Also a clear theme: Frontline/middle managers see what's coming much better. Many are struggling hard to do the right thing. "Leadership" is often blissfully unaware and an active blocker/distraction.