9wzYQbTYsAIc

Next thing to go will be loops and scheduled tasks, if they keep needing to trim usage to fit in the available compute, I suspect, if ‘claude -p’ is essentially gone, now.

Or start switching to open-weights, local LLMs for basic development. Would rather invest in my own hardware than Anthropic’s, tbh.

Exactly, the weekly limits are the real limiting factor. If you really push it, you can easily hit the weekly $200/mo Max limit in a day.

Have any ins? ;)

If you think in terms of quantum mechanics and density matrices across higher dimensions, then, yes there are interesting geometries that arise.

I’m exploring some “branes” that might cleanly filter in emotional space.

Consciousness: do you believe plants are conscious? Ants? Jellyfish? Rabbits? Wolves? Monkeys? Humans?

Even fungi demonstrate “different communication behaviors when under resource constraint”, for example.

What we anthropomorphize is one thing, but demonstrable patterns of behavior are another.

See also: Process Philosphy [0]

[0] https://plato.stanford.edu/entries/process-philosophy/

Pretty easy to test, I’d imagine, on a local LLM that exposes internals.

I’d suspect that the signals for enjoyment being injected in would lead towards not necessarily better but “different” solutions.

Right now I’m thinking of it in terms of increasing the chances that the LLM will decide to invest further effort in any given task.

Performance enhancement through emotional steering definitely seems in the cards, but it might show up mostly through reducing emotionally-induced error categories rather than generic “higher benchmark performance”.

If someone came along and pissed you off while you were working, you’d react differently than if someone came along and encouraged you while you were working, right?

It might simply reduce down to a big batch of sliders and filters no different than a fancy audio equalizer: Anthropic was operating on neurons in bulk using steering vectors, essentially, as I understand it.

Hah, I have been thinking about trying to study LLM psychology, nice to see that Anthropic is taking it seriously, because the mathematical psychology tools that can be invented here are going to be stunning, I suspect.

Imagine coding up a brand new type of filter that is driven by computational psychology and validated interventions, etc

> Force-set to 0, "mask"/deactivate those representations associated with bad/dangerous emotions. Neural Prozac/lobotomy so to speak.

More complex than that, but more capable than you might imagine: I’ve been looking into emotion space in LLMs a little and it appears we might be able to cleanly do “emotional surgery” on LLM by way of steering with emotional geometries

They already can, but, only if you really invested in a performant computer in last few years. If you really invested 10 years ago, you might also get lucky, but that RTX and high VRAM will be key.

Oh, or you could also use a Mac or recent iPhone, they do fine too, today.

Tomorrow is only speculation, but it looks promising, with all the new optimizations and realizations that LLMs aren’t the king of the hill, they are an option on a spectrum of choices.

Optimized small models might surprise you.

I’m playing with 3d positions derived from higher dimensions, right now.

Phew, just get the Qubes to spin up on demand with each agent and that could be pretty neat.

It ought to only get better as it gets honed at an even faster pace than before, utilizing techniques and algorithms that would have been out of reach due to outside constraints.

My point exactly, embedded devices are the closest software gets to actually being built by licensed engineers. The expectation can often be that you are an electrical engineer by training, where licensure is a viable path, unlike in software engineering.

Node RED is still unwieldy for the masses, as easy as it is for a consumer to install, it’s not necessarily as easy to use.

Consumer grade automations built on node-RED? I suppose it depends on the market, but most people aren’t going to want to fiddle with it, I suspect.

A plugin for Chrome might be able to take off though, or some killer mobile app, but it needs to run on a cheap phone and control things without having to keep track of loops and logic and variables and all the fun stuff.

Similarly short on reply here, but quickly: IFTTT: hah, I agree. It was awesome when it was more about IoT than Spotify to Google Sheets.

And re: Zapier: yes, that’s the key to Zapier, from my experience: usage in marketing and the “power user” base.

Re: shortcuts: (I live in the Apple ecosystem) Shortcuts + AppleScript is gold on macOS. Shortcuts + iOS is about to be game changing - it already changed the game, it’s just nobody has been playing it, because it’s not “fun”.

After Siri+Gemini+Shortcuts, everyone will be playing it, I suspect, even on Android, it will get built somehow.

Yes, but slowing down to avoid hazards is sometimes important.

Medical devices and such are the only places I’d expect to see the need for certified products. By extension, in the new era, we really ought only expect certified software where we expect a duty to care from the software system (or any other assigned duty)

What can we do with 1MB of RAM is just as important as what we can do with 1000GB of RAM

Solarpunk + https://permacomputing.net/

That’s for everyone

> More importantly, it is almost impossible for engineers to be as well incentivized to spend extra time exploring edge cases in something they already believe to work than to ship a feature on time.

Personal liability and professional insurance works for all the actual “professions” in the US, to some extent, right?

It might be time to start the considerations for professional licensing for platform scale or commercially published software.

Yes, but police and military are both law enforcement, on one level, but each are very different from the other.

Even the military have police, right?

edit: ultimately, it comes down to the importance of independent audit, the builders and the breaker/fixers are very different groups in engineering.

Somehow hospital CEOs and doctors/nurses have managed to both eat the liability and make a living.

I think the same patterns can be applied here.

If the only thing LLMs did was clear enterprise technical debt backlogs, the end consumer would still benefit from the technology.

If LLMs do nothing but clear enterprise technical debt, the consumer might benefit from that alone…

If engineering owns quality, it ought to also own the liability, too.

That would put the damper on the pipe dream pretty quick. Probably more healthily than any data center ban could ever do.

If engineers were licensed, bonded, and liable, things would go very differently.

* speaking as having been a practicing software “engineer” for a decade

> I don’t understand the reasoning here why QA shouldn’t be engineering.

Who watches the watcher, right?

That aside, the core idea is the same as the principles of independent audit, peer review, or even simply just specialization.

Red team / Blue team?

> Have engineering own quality

The moment that happens it will either be re-outsourced to QA anyways or quality will become a question of licensing and bonding of professional engineers