kaycey2022

What risk would Harvey the company manage for them? Security appliances work, and vendors in security deal with tech that works. What is Harvey making certain in this tech?

Knowledge Collapse in action right here. Our civilisation is like a dying creature desperately trying to conceive a successor, not realising the act itself is speeding our deaths.

Have you seen Attack on titan. Watching that whole show, half the time you dont know why something is happening, except that it is cool. But once you know the whole story, you can piece things together no problem.

The unsolicited comparison doesn’t work when entire businesses will be defunct without it

I think Google’s own textbook on SRE has an example in its very first chapter where everyone gets locked out of their bus fleet WiFi thanks to their secure system reaching an unforeseen state

This feels objectively worse than writing down a password somewhere

One only has so much mental bandwidth. You will either throw yourself into the math and programming, and the serious publications which is way less sexy and appealing than the fantastical ravings of the AI safety and alignment crowd. Sadly only very few hyper connected and highly intelligent would have the capacity to read everything and know everything. Most would only have cursory information about the drama surrounding alignment if they instead focused on the reality behind AI.

No because i am still losing 50% of my weekly quota using sol on high.

Like I said I dont have much mobile experience to make a claim. Native apps have their own view and accesibility hierarchy. But even there, React Native would be a better choice because its components become native platform views which would directly be located by 3rd party apps like Appium etc compared to flutter.

The biggest negative with Flutter is web. Because most of the UI is canvas-rendered, DOM based tooling like session replay, analytics, accessibility audits, and browser automation require specific instrumentation. That reduces third party choices you have unless you invest in your own tooling and who has time for that. I can't imagine the situation is much better in mobile.

I've been using GPT through opencode for quite some time on linux. I have had a great time with getting it to help me through computer use and it has been a game changer for me.

For instance recently, media downloads on my NAS became quite a bit slower. I asked it to investigate and it quickly got back to me saying the issue was the ethernet link had been downgraded to 100Mbps from 1Gbps. It even went through journalctl to tell me when this had happened. To fix it I just had to plug an ethernet cable out and back in. Now this is the kind of thing, earlier I would have to spend an evening on. But given an open system like Linux, a well made safe model just makes it so much more accessible than having to RTFM for one off things I am sure to forget in a month.

I dont really let it run loose through my systems, and keep an eye on the thinking traces it puts out and the permissions it asks for. But now I dont have to slog through manuals and deal with gruff people on the internet. I can choose to do so after the fact, depending on how much free time and curiosity I have.

What! They replaced the native mac app with this?!

That's it? It doesnt feel right. This feels good enough for a casual dinner table conversation and not much more.

If the copying was deliberate then why admit to the similarity? He should have just blocked the guy and continued as if nothing was wrong. Admitting the plagiarisation lead to a worse outcome every time.

It seems apparent to me that task complexity can’t be determined by prompt alone. How? A prompt is just a simple rambling. An agent will go through many many tool calls and steering just to arrive at the right approach.

A serious router therefore needs to build up a dataset of how different models responded, end to end, to different tasks on different contexts. I won’t comment on whether the current frontier models can reliably judge these outputs, but I am sceptical about that. And moreover look at the state of evils! They are gamed to hell and keep losing credibility.

A more difficult problem for router builders is that they are working on an opaque system behind an external API. How can you reliably guarantee model behaviour when model behaviour has been shown to deteriorate under arbitrary conditions that have nothing to do with the task given? So much investment only to be an AI company that can get rug pulled by the real AI companies at any given time.

I would think the only people who can come up with good routers for a collection of models are the inference providers themselves. Because theoretically they have full control of how their models are served. And inference is not zero cost or cheap for them either. And going by OpenAI’s experience routing is not an easy problem for them to solve either. And they don’t have the incentive to route you to cheaper models and reduce costs for customers at the same time. Routing objective for them is to increase their own profits.