j45

Very possible, I think in other areas it could be helpful.

It's critical that specialists who know whatever they do, work with AI to see the path ahead for their area, while the mega models try to be a single mega model for everything.

The comments here about A/B testing are one thing, the real wave that will be massive is unprecedented personalization compared to what exists today.

New model releases that have positive reviews should come with a nerfalert reminder service to make hay until it's shaped and shaped and shaped.

Very informative thanks.

It’s still a big thing to shop, iteration is the gift.

I think visualizations can be inspirational but often need to be personalized. Whether it’s audience, content, or presentation style the more I watched the HN feed, the more I wanted to be able to adjust and tweak certain things.

It was less about video at one point I could even drive and listen as an a podcast.

I would be surprised if this was not already systemic and endemic across the retail space preying on people who have compulsive spending, gambling issues.

This is an interesting KPI

This is pretty cool, I'd want to see the visualizations a little different but that's a personal preference.

Maybe some people just ship and post and don't look back in terms of scrutiny / comparing.

There's lots of approaches out there that say if you don't ship something embarrassing, it's too late.

I think this is the main point I was trying to make and our exchange helped me bring it forward, thanks.

It shouldn't be accepted, maybe it's relative to the amount education (and educators) are valued by a society.

Specifically it's important to ask for more than a few examples.

Agreed, and the vast majority of personal projects that are released as open source don't get attention, traction, or contributions.

In this case, someone shipped something that works for their use case, which is a great deal more than talking.

Coding might not be solved out of the box with these providers, but there are increasingly setups and harnesses that do have a great deal of it solved.

The last time I checked, patents.

LLMs could be asked to research extra projects.

It's valid that someone just wanted to build something like this for their own purposes.

I'm no expert, but did your lawyers clarify if a statute of limitation start from the date you learned there might be a discrepancy, instead of all those years ago?

While no one's hands might be clean in this, at the end of the day the party with the resources and expertise is equipped differently.

It might not hurt to get some more opinions even if they end up in the same place.

The non-coursework based exam can also probably be gamed in the end.

Students could just use the AI to teach/tutor the material to them instead, but the institutions are clutching the pearls too tightly.

That makes sense. I was focusing on the DNS step itself.

Since the agents are set on endless loops of rumination (through every example ever) I can see how it might go further.

My other concern would be the clearly defined gaps between researchers who don't applied research let alone crossing the bridge into the real world of operationalizing things let alone implement.

Letting something rip across multiple domains without understanding what each of those legitimately have done for the past decades is pretty eye opening.

So the LLM was able to look up a basic way to reroute things to get to their destination (likely well available and trained in the corpus) and it's surprising?

What's surprising is the surprise the security testers are explaining.

By setting an outcome to reach an endpoint, and to find all possible ways there, would this not be in the realm of possibility if an agent is reasonably in control of a vps?

Having the vps locked within a network layer it can't see or get out of is pretty common practice when setting up IaaS / PaaS.. sans-llm.

Maybe I'm missing something here, what confuses me is how something so relatively simple can get such prominent coverage, it's hard to imagine this kind of ability is still relatively new or surprising to folks working at the major models, unless they aren't hiring for network experience?

Reading about this makes me wonder what Japan was like during WW2

Did his ever catch on to begin with?

The transcripts of mental health professionals could likely have an improvement in the baseline below-average experiences of most folks with such supports.

In other words, mental health professionals will resist this technology to replace them until they realize they can put it in front of people like a new kind of web form, at which time the same will become amazing and wonderful.

At the very least, a tool like this could serve as an anti-virus and firewall for poor and harmful experiences from mental health professionals towards clients.

I feel the same way about creatine (and increasingly protein).

One thing that might help me notice creatine more is that I haven't drank much caffeine for some reason.. and the longer I've been able to put it off or minimize it, the more of an unfair advantage it has become when I've started.

It's not always a call that wraps an llm.

The LLM only does average returns from average inputs.

I'm looking for the pile of studies I had come across, here's a few to help link to more.

Cerebral Creatine levels seem to be a different thing.

Creatine and TBI:

https://health.mil/Reference-Center/Publications/2025/09/25/...

https://www.ncbi.nlm.nih.gov/books/NBK209321/

Creatine supplementation for naturally declining creatine levels:

https://jpbs.hapres.com/htmls/JPBS_1766_Detail.html

https://pmc.ncbi.nlm.nih.gov/articles/PMC10526554/

I thought it was too, then I started learning about how so many studies about Creatine were only in the body, and not the brain..

And then there were the discoveries of creatine in the brain in studies.

Not a typo, 20g+ a day.

Dosing for gym exercise is different than dosing for excess creatine to reach the brain.

Well studied, checked with my doctor, including for TBI. Obviously everyone should check for themselves.

It's beyond crazy, lol. How many grams are you doing a day?

It has replaced in some ways caffeine for me.

The part of where creatine wipes out sleep deficit sounded like a stretch, but it definitely helps.

Creatine is one of the most studied supplements.

It sounds you have the hardest part of it underway - consistency.

There's lots of studies - if you can get over 20g per day it is noticeable to the brain and energy. Adding a few grams a week until you're up there I found it noticeable. 20-30g seems to be a noticeable range.

Supplements aren't always like a coffee spike, they build up and sustain quite well.

It's ok to downvote this, doesn't mean it has to be comfortable to have some chats, it's where we all can learn by starting with ourselves.

Edit:

Not fishing for upvotes.

It's ok to realize something you liked using might come from something that's not good and working through that.

Other people who are willing to overlook it: https://omarchy.org/patrons/