I realize this is not scalable, but I’ve come to the personal preference that sycophancy be overt. LLMs are always steering in a direction and I find it a good reminder that they are just as incapable of objectivity as humans. TBD, but I think I’d prefer that fact plainly visible where I can see it.
Just working on my own stuff so YMMV, but from a cost reduction standpoint, the two most outsized ROI wins came from making sure the agent runs all terminal commands in quiet and using a codebase index mcp to speed up understanding and reduce full file reads [0]. I've also found the latter also dramatically improved the quality of output.
We actually had a lot of the tooling and process rules we now give out to LLMs so that they do what we want them to do optimally figured out and theoretically in place way before LLMs.
Turns out everyone had just been vibe–managing people this whole time so there was still that guy burning salary "tokens" going through a million lines of on–demand grep output.
This tweet is written as parody, but it seems self-evident from reading Trump's tweets that they do not all come directly from the president himself. Most political offices delegate social media to an internal team, presenting as if from a unified "source" when really they speak for an organization. Given the fierce competing factions within the administration - and the sort of kreminology political reporting has been reduced to in the current environment - this is precisely the kind of modern situation where textual analysis is helpful in determining who is speaking.
Most programming best practices were created to solve for the same problem LLMs face: limited context. The principles around well-crafted code strove to make it modifiable by future agents who are not the author. Maintainable code stabilizes around the invariants of the domain it address while providing a spectrum of modifiability to future users, running from UI > configs > cleanly abstracted code > core.
I do wonder if there will be a convergence between sodium-ion battery architectures and cheaper, renewable-powered desalination. Could industrial seawater mining be competitive as a sodium feedstock source?
I just realize we have heaps and heaps of seasalt sludge around desalinization units. Dirty sludge, but salty nevertheless, right there at the fingertips. Maybe some of it could be useful?
I think the limitation to team "let-people-do-what-they-want-even-if-it's-bad-for-them" is that it's rooted in outdated assumptions about what free will and coercion look like. Broadly speaking, libertarian notions of negative freedom assume a model of coercion with a very small footprint, primarily the threat of immanent physical violence. Similarly, it sees the exercise of free will as a binary action, rather than a spectrum of ability.
We entered this era a long time ago, where psychological insight and computational or chemical power can combine to override people's ability to make free choices. But I'm still not sure there is a widely shared philosophical or ideological framework that has fully digested and responded to these new realities yet.
"It's not a war on drugs, it's a war on personal freedom. Always remember that" is all well and good but pretending 1960s ditch weed and fentanyl are a single problem with a common prescription either way is misguided.
I've been running Claude Pro at home, supplemented with Deepseek configured in Claude Code. I've had decent luck throwing Opus (and briefly Fable, RIP) at architecture / product problems and producing plans to hand off to Deepseek (I personally find v4 to operate somewhere between Opus and Sonnet in capability).
Lately I've been able to cut down on token usage with context-mode and codebase-memory to wring more out of my subscription, as well as doing things like make sure all terminal operations run in quiet mode. I've found codebase-memory particularly effective: it creates an index of your codebase that the agent can query for code tracing without reading all of the associated files, and I've also found it more accurate at analysis
> The new plant in Minnesota will be big enough to deliver 300 megawatts of power and store an enormous 30 gigawatt-hours of energy, making it the largest battery by capacity that’s been announced so far. By comparison, that’s more storage than all of the battery projects built in the U.S. in 2024 added together.
That's to power a single data center though, how would that scale?
If I'm doing the math right, Minnesota used 65.7 TWh of power last year so to store 3 days worth of power just for that one city we would need a battery 18x larger than the one mentioned here.
I can't imagine we could ever scale such storage capacity for all energy use, let alone all the wind and solar required to fill it.
Sodium is an interesting chemistry, though it has different voltage curves than lithium ion once hardware is built to match it they may scale well for industrial use.
That still doesn't avoid the more fundamental math of having to store such massive amounts of energy though, even if you skip batteries and pump water to retention ponds uphill.
Even for small scale residential, the recommendation is to store 3 days worth of average usage to handle stretches of cloudy days and to have a generator for the times when that still doesn't cut it. You also need enough solar that 4-6 hours of generation can fill those batteries back up after a stretch of cloudy days.
You also have to contend with frequency issues. This is what took down Spain's grid, they had turned on a ton of solar at the time - with many gas plants offline a seemingly small dip below 60Hz really wrecks much of the system when it wasn't designed to handle those swings and triggers multiple safety mechanisms.
This is the answer for me as well. My partner and I try to be intentional about giving each other at least an evening a week to go do something social, but it doesn't work out nearly that often because everyone else is juggling their own kids' schedules. So even if I didn't personally have kids, I would still be facing the same issue.
