voiper1

The blog claims rust chosen mainly to address memory issues, which rust is a better language for. So, success would simply be less new memory errors / easier to patch old ones.

At least I've done what I can do, but we can't save people from themselves.

Why should doctors NEED to save people from themselves?

The default should be what the people in the industry have learned, with full permission to say "For myself, I have written a legally binding document that this is my personal wishes. I suggest you make that decision for your loved one, too."

Patients have the ability to ask for more, but there shouldn't be a constant need to save people from inadvertently choosing risky/painful low payoff medical care!

Blockchain... NFTs The problem is, the same dudes who were pumped for all of that bollocks now won't stop wanging on about Artificial Intelligence.

I was firmly in the camp that blockchain was not a viable solution to any problem, and that NFTs sound stupid. I think AI is much different than that list. So, there goes your argument?

I hear your pushback, but that I think that's his point:

Even seasoned coders using plan mode are funneled towards "get the code out" when experience shows that the final code is a tiny part of the overall picture.

The entire experience should be reorganized that the code is almost the afterthought, and the requirements, specs, edge cases, tests, etc are the primary part.

My theory is that even if the models are frozen here, we'll still spend a decade building out all the tooling, connections, skills, etc and getting it into each industry. There's so much _around_ the models that we're still working on too.

I definitely didn't expect one-shot to mean "let it run itself in an indefinite loop"

Surely there's AI usage that's not morally reprehensible.

Models that are trained only on public domain material. For value add usage, not simply marketing or gamification gimmicks...

Of course my first thought was: Let's use this as a tool for AI searches (when I don't need recent news).

Never seen that one, thanks! Alt text: "Our brains have just one scale, and we resize our experiences to fit."

(And obligatory https://xkcd.com/1053/)

Wow, looks like a tremendous commitment and depth of knowledge went into this one-man project. I couldn't even read the whole write up, I had to skim part of it. I'm super impressed.

I know tomato (acidic) will make holes in aluminum foil but I didn't know more than that.

I guess today's my day: https://xkcd.com/1053/

Cool people are largely perceived to be extroverted, hedonistic, powerful, adventurous, open and autonomous.

But "utter crap" isn't just an aesthetic issue - that can mean all kinds of bugs and malfunctions!

He did say he doesn't know if the center has cash inside... but a hollow core definitely defeats the display purpose!

Chrome web store link got truncated, this is the link from github: https://chromewebstore.google.com/detail/cpdown/knnaflplggjd...

Will give it a try, thanks!

I don't like the thinking time, but for coding, journaling, and other stuff I've often been impressed with Gemini Pro 2.5 out of the box.

Possibly I could do much more prompt fine-tuning to nudge openai/anthropic in the direction I want, but with the same prompts Gemini often gives me answers/structure/tone I like much better.

Example: I had claude 3.7 generating embedding images and captions along with responses. Same prompt into Gemini it gave much more varied and flavorful pictures.

The eiruv only works as a loophole for the added stringencies by the Rabbis. Anything that's considered totally public in actual Torah Law (which is a big debate what exactly that is) is not subject to the permissibility of creating an eiruv.

Isn't "left or right" _followed_ by rationale asking it to rationalize it's 1 word answer - I thought we need to get AI to do the chain of though _before_ giving it's answer for it to be more accurate?

The benchmarks in many ways seem to be very similar to claude 3.7 for most cases.

That's nowhere near enough reason to think we've hit a plateau - the pace has been super fast, give it a few more months to call that...!

I think the opposite about the features - they aren't gimmicks at all, but indeed they aren't part of the core AI. Rather it's important "tooling" that adjacent to the AI that we need to actually leverage it. The LLM field in popular usage is still in it's infancy. If the models don't improve (but I expect they will), we have a TON of room with these features and how we interact, feed them information, tool calls, etc to greatly improve usability and capability.

I've been using that as a test of new LLMs - and do it in a specific style.

I assume they mean when the phone is "turned off" meaning the screen is off, not powered down.

From the article: "... but did not respond to numerous questions about other aspects of the group’s accounting."

It's not "nitpicking" when the reports of where/how much they are saving money -- their purported goal -- is _fundamentally_ inaccurate in many circumstances that can be verified. And even worse for what that implies about everything else that can't be verified.

My query generated 17 steps of research, gathering 74 sources. I picked "Deep Research" from the modes, I almost accidentally picked "reasoning".

Wow, that's so fun. Just upload and generate assets super easily... queue the next one while it's working.

To work around this, we had to change the assertion logic in some tests to check the name and code, instead of the message. This is also the standard practice for checking error types in Node.js.

Sounds like something they should try upstreaming?

Now they'll need to track all the tests to manually modify/import...

Cute. First thing I did though was to see if moving my mouse or clicking affected it. Doesn't seem to, please add that!

The first question is always: which model? Which fortunately you at least addressed: >free plan of ChatGPT, but I can remember if it was 4o or 4.

Since chatgpt-4o, there has been o1-preview, and o1 (full) is out. They just announced o3 got a 25% on frontiermath which is what this article is a reaction to. So, any tests on 4o are at least TWO (or three) AI releases with new capabilities.

I read both those articles, but I still don't get how to do it. It seems the idea is that more of the embedding is informed by context, but do I _do_ late chunking?

My best guess so far is that somehow I embed a long text and then I break up the returned embedding into multiple parts and search each separately? But that doesn't sound right.

I thought embedding large chunks would "dilute" the ideas, since large chunks tend to have multiple disparate ideas?

Does it somehow capture _all_ of the ideas, and querying for a single one would somehow match?

Isn't that the point of breaking down into sentences?

Someone mentioned adding context -- but doesn't it calculate embedding on the whole thing? The API Docs list `input` but no separate `context`. https://docs.voyageai.com/reference/embeddings-api

Related XKCD: https://xkcd.com/1172/