zeroxfe

> And, you as the client can verify whether it works

How do you do that? Cookies are typically opaque (encrypted or hashed) bags of bits.

Yeah, I was thinking the same. I have two Dyson vacuum cleaners, one purchased about 9 years ago, and the other two years ago. Both are excellent, and I still use the old one for my basement.

This really depends on the failure modes. In general, humans fail in predictable, and mostly safe, ways. AIs fail in highly unpredictable and potentially very dangerous ways. (A human might accidentally drop a knife, an AI might accidentally stab you with it.)

I've never used LLMs for this, but as someone who's been through a lot of sports-related injuries, I find doctors more or less useless (except for prescribing painkillers and performing surgeries.)

No doctor or physio has ever been able to fix my chronic issues, and I've always had to figure them out myself through lots of self-study and experimentation.

> If it was pulled into Rust stdlib, that team would be stuck handling it, and making changes to any of that code becomes more difficult.

I think Rust really needs to do more of this. I work with both Go and Rust daily at work, Go has its library game down -- the standard library is fantastic. With Rust it's really painful to find the right library and keep up for a lot of simple things (web, tls, x509, base64 encoding, heck even generating random numbers.)

There's no single ordering -- it really depends on what you're trying to do, how long you're willing to wait, and what kinds of modalities you're interested in.

> “Ok, so…” is wasted tokens

This is not the case -- it's actually the opposite. The more of these tokens it generates, the more thinking time it gets (very much like humans going "ummm" all the time.) (Loosely speaking) every token generated is an iteration through the model, updating (and refining) the KV cache state and further extending the context.

If you look at how post-training works for logical questions, the preferred answers are front-loaded with "thinking tokens" -- they consistently perform better. So, if the question is "what is 1 + 1?", they're post-trained to prefer "1 + 1 is 2" as opposed to just "2".

FYI, Your website (https://getstream.io/) is broken :-)

Application error: a client-side exception has occurred (see the browser console for more information).

> What do you really need out of a cloud?

I need a cloud to be reliable and secure. I've used Azure extensively and it's neither. I'll take GCP or AWS over Azure any day.

You can't get 100% reliability from a human either.

It's not. You should actually try out the exercise. (I used this approach to build partial perfect pitch, i.e., to sing/identify a small number of specific pitches.)

Close your eyes and try to imagine a song that you know really well. Imagine the original version playing on your phone/mp3 player/cd/record. Pick a stable note from that song (for me, the third note of the beginning of "Tears in Heaven" is a solid A.) Try to sing it and match the pitch in your head.

As you practice it you'll get better, and do it faster, and over time even be able to recognize it in the wild.

That's not how I read it. It's more about having a consistent approach to managing error types in large code bases. This is a common problem with exception-based languages too.

There was tons of duplicate code, unnecessary code, dead code, etc. There was also a lot of code for which CPAN modules could entirely replace. (Also, I'm a workaholic who obsesses about a problem until it's fully solved.)

Okay, so when I worked at Sony about 25 years ago, I got assigned this project to fix our order management system, which was extremely slow, and kept crashing.

I jumped in and started digging around, and to my horror, the OMS was a giant set of shell scripts running on an AIX server, which evolved over a decade and was abandoned. It was over 50,000 lines of code! It was horrendous and shit kept timing out everywhere -- orders, payments, and other information were moved from server to server over FTP, parsed with complicated sed/awk, and inventory was tracked in text files (also FTPd around.)

At the time, perl seemed like the most practical way for me to migrate the mess -- I rewrote all of the shell piece by piece, starting with the simplest peices and replaced them with small perl modules as part of a larger perl application, refactoring along the way. It took me 3 months and I moved the whole thing to about 5000 lines of perl, and it ran 10-100x faster with almost none of the failures in the original system.

As terrible as it was, it's one of the most satisfying things I've ever done. :-)

> fundamentally flawed tech, since maybe Theranos

That's a pretty dramatic claim. We've had to (and still have to) deal with the same class of problems when going from analog -> digital in chips, communications, optics, etc. etc. The primitives that reality gives us to work with are not discrete.

It's readable if you're familiar with the RAII pattern which is used in languages like C++ and Go.

That's not the whole point of the training. It's just (very loosely) a measure of loss used during pre-training. There are many post-training and alignment stages in a typical model that are designed to reward high-quality responses.

Technically, yes, it's impossible to guarantee that it won't just regurgitate source material (which is mostly around the tails of the data distribution), but the whole point of training is to build generalized intelligence.

This is unconventional use of the term "distributed locking". This alternative just punts the hard part of locking to the storage system.

> This overcomplicates things...

You're misinterpreting the problem described, and proposing a solution for a different problem.

IPFS is probably the closest open-source thing here, but the UX for non-nerds is not great.

Came here to say something similar. You also notice that before any verbal thoughts arise, there are "primordial" thoughts, which are "felt" (sometimes as emotions.) These can instigate huge chains of verbal, visual, auditory thought, in turn generating more emotions, causing a (occasionally vicious) feedback loop.

>>chunking objects in memory for better recall //

> Can you share your source on this?

I haven't seen the research on this, but it makes intuitive sense to me as a musician. It was the only way I could learn long complex pieces.

If you're doing it for the prize, then you're not the targeted audience :-)

In the early days of Google, when I worked on websearch, if people asked me what I did there, I'd say: "I answer all the queries that start with S."

> all evidence suggests that there's no information coming into the simulation from the outside

sorry, which evidence suggests this? (it's not hard to imagine an external observer feeding back into the simulation)

(btw, I agree that the argument is flawed for the reasons you cite -- I don't agree that we have any evidence around whether or not there's information flow in/out of this simulation.)

> ULA wants photographers to work for free getting pictures in the media.

That seems like a stretch. I'm sure ULA would have no problem getting pictures in the media without hobbyist photographers.

> I have very high confidence that a real and effectively-correct theory of quantum gravity will remove the singularities.

What gives you this confidence?

If you're a beginner, you'll need to work your way up to at least 45-minute sessions. You're not going to be able to enter jhanas in 20 minutes unless you're very experienced and entered them consistently for a long time. For me, it was when I got to 1 hour sessions when I started to experience the deep absorption for jhanas.

I highly recommend "With Each And Every Breath": https://www.dhammatalks.org/books/WithEachAndEveryBreath/Con...

Also, the "Waking Up" app, which has a fantastic collection of guided meditations, dharma talks, theory, etc.

"The Mind Illuminated" is a really good book too, with a very specific (and effective) technique taught in a lot of detail.

One of the things you quickly discover when you start meditating is how deeply your breath is connected to your mind and body. You can literally detect a thought forming before it does simply by sensing subtle changes in your breathing. You'll also notice how the most trivial thoughts also have a physical manifestation in your body, e.g., mild tension in your eyelids, or a tingling in your abdomen, etc.