amoss

Somewhat tiring that as alway any criticism is reduced to "but have you tried this on the latest model".

Sometimes this also happens because the design/spec never existed, but hopefully not in the industries under discussion.

In many codebases when you see this happening it is because someone reported a bug and the dev fixed the narrowest instance they could. Typically if(some specific case) do_fix() else do_normal(). Over time this fragments meaning in the source and makes it harder to reason about until it is a giant pile of slop.

The thing the dev should do that often doesn't get done is to take the information about the undesired behavior back up to the design/spec level and rework the definition to account for it. This doesn't normally get done because it takes longer and it is conceptually more difficult than the patch.

This is something that LLMs can accelerate significantly and the result is a shallower gradient of technical debt over the long term.

Your tool looks interesting but the readme file is very "wall of text" heavy and example light. In comparison the site for this tool shows exactly what it does. Perhaps that explains the difference in response. This is a classic case of the need for "show don't tell".

You should let them eat cake.

Cloud services expose their UI/UX through a web-browser will all of the pain points of running a stateful blob of javascript on the client, talking through a mostly stateless protocol to a "mess of stuff" that aims for eventual consistency in the backend.

The old folks, who are retired and dying according to this thread, mostly grew up using local applications with direct control between UI/UX and action.

Good to see that people still have this spirit of rolling their sleeves up and doing something like this for fun. Underneath it there is a very real point about mono-cultures and the increased magnitude of the impact of a risk, although more eyes checking one implementation should reduce the probability.

huge if true.

meanwhile this bill gates will be remembered for asking his friend epstein how to secretly treat his wife for the std that he gave her.

But the reason why it remains load bearing is key.

Some of it is well sourced but the remainder is well sauced.

No, it is the application of learning and that is why learning is central to the definition tgat you pointed at.

Quoting directly from the dartmouth conference:

"every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it."

If you place an LLM into a harness, alongside evaluation, feedback and problem decomposition / solution integration - it is still an LLM?

There is an LLM acting as a component in a larger system. But that larger system is not an LLM. Calling it an "AI" is indeed an act of marketing as there is no learning / adjustment as we would expect from an intelligence, but calling it an LLM seems to be inaccurate. So what is it?

> Modern models, when properly managed with a human in the loop, write higher-quality code than humans and introduce significantly fewer bugs.

I don't think anybody believes this, and interjecting it into every thread is not really convincing anyone.

What you have to remember is that the people who decide who to appoint into these roles are another step removed from the problem domain. They will have no programming experience, or the ability to evaluate programming experience. They will try and rely on metrics or some "data-driven" approach to deciding who to appoint.

What kind of data will they look towards? Here, we have a precedent from frantically points to absolutely everywhere around us. So the people with "engagement" and "reputation", i.e. they gushed on their blog and farmed engagement, will be exactly who gets appointed to make the decisions.

Tried it after seeing the comment about it yesterday and loving it so far. Very clean, easy and fast to build. Performance is great, and the minimal UI is a breath of fresh air.

I'm on the Swedish list and I get exactly zero spam calls. As the parent post pointed out it is country specific.

Whether they are or not is irrelevant to the difference- there is still an explicit division between training and inference, with reinforcement of the statistics of the training set.

I think it is uncontentious that we are not designed at all. But to address the intended spirit of the question: are we restricted to output that is a close fit for our training set?

I would argue that we are not - because we do not have a rigid partition between training/test. Our ability to reason speculatively rests to some extent on ability to produce outputs that we have not seen before and which are statistically not like that which we have already seen. How we know which of these outputs to keep, and which to discard is (afaik) an open question.

The tu quoque argument doesn't really work here. LLMs are specifically designed to output either material from their training set or instances that look statistically like it. Humans are not.

If you are relying on live updates to change state in a dynamic language then you are not doing it "surgically", unless there is some other definition that means hitting it softly with a large rock.

Kind of weird how LoC has become a metric for people to chase again.

I don't think you can describe his beliefs using booleans like that: you have to use a numeric scale. It would be be correct to say: Elon would need a hell of a lot of ketamine to believe a colony on mars is a possibility.

Alternatively you may want to be a passive investor using the current rules for index inclusion, rather than having them altered to favor this loss-making trashcan on fire.

> The world seems to be fragmenting, into those that see the value in the latest from Google, and those that resist changes like this.

This reads as a strongly closed minded claim that has been "whitewashed into corporate appropriate speech" by an llm. If you cannot understand any validity to the other side of a debate then you are not engaging in discussion, no matter how your claims are dressed up.

That is the ugliest Ferrari I've ever seen.

kind of wild that you think there has been no shift in culture between 1970 and 2020

with a mastercard from a swedish bank that is the experience that i get. all online transactions pop up a page from my back with qr code, this is authenticated through an app that shows me the transaction details and requires pin confirmation.

Dead code elimination is run multiple times, including after other optimizations. So code that is not initially dead may become dead after propagating other information. Converting dead code into an error condition would make most generic code that is specialized for a particular context illegal.