Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Python 3.14 compiled to metal – no interpreter

github.com

Post reply on HN
Print view View original

121–130 of 140 posts

Re: Python 3.14 compiled to metal – no interpreter

#121

Post by coldtea »

LtWorf wrote: post #111
coldtea wrote: post #76

Earlier quoted context omitted.

Doesn't matter what AI companies do, since AI companies just "move fast and break things" not caring for bug fixing but for iterating quickly on their agents. That's a business decision, not an AI limitation. If you use AI yourself, with a focus on bug fixing and stability, you'll find that AI can fix bugs just fine.

It matters, it shows the limits of the technology, and they have all the interest to showcase how good it is (and are failing to show it can fix bugs)

They have little interest to "showcase how good it is with doing that" since (a) people already see it's good and are hooked, (b) they don't want to stop the pace of changes and fall behind on features by focusing on stability and bug fixing.

Re: Python 3.14 compiled to metal – no interpreter

#122

Post by jpfromlondon »

CookieCrisp wrote: post #71
bloppe wrote: post #56

Earlier quoted context omitted.

Hypothetically, maybe. In practice, probably not.

If it's valuable enough to someone, and it isn't keeping up, someone will pay. If it's not valuable enough for someone to pay, then who cares?

Plenty of important things have been born of passion without necessity.

Re: Python 3.14 compiled to metal – no interpreter

#123

Post by ubercore »

coldtea wrote: post #64
ubercore wrote: post #44

Earlier quoted context omitted.

The problem is the _way_ AI will solve an AI bug. I've seen the loop countless times. There's a creeping complexity and brittleness that creeps in over time as more and more complexity is left purely to the LLM agent. It will become unsustainable without a human understanding and making course corrections at some point.

In my experience, it just needs some high level guidance. And it's quite easy to ask an AI to refactor a certain way too.

Been there done that. My point is that even with Fable being a big improvement, it still needs constant feedback.

The loops themselves are a lot better, but it still needs judgement calls, and Fable will often take an odd direction, and if you don't catch it, that odd choice will compound as it continues to layer on top.

Re: Python 3.14 compiled to metal – no interpreter

#124

Post by coldtea »

ubercore wrote: post #123
coldtea wrote: post #64

Earlier quoted context omitted.

In my experience, it just needs some high level guidance. And it's quite easy to ask an AI to refactor a certain way too.

Been there done that. My point is that even with Fable being a big improvement, it still needs constant feedback. The loops themselves are a lot better, but it still needs judgement calls, and Fable will often take an odd direction, and if you don't catch it, that odd choice will compound as it continues to layer on top.

>Been there done that. My point is that even with Fable being a big improvement, it still needs constant feedback.

Even so, if it does 80% of the work itself, that's still a 5x improvement.

Plus it keeps the human coder in control and in the loop (and in a job).

Re: Python 3.14 compiled to metal – no interpreter

#125

Post by LtWorf »

coldtea wrote: post #121
LtWorf wrote: post #111

Earlier quoted context omitted.

It matters, it shows the limits of the technology, and they have all the interest to showcase how good it is (and are failing to show it can fix bugs)

They have little interest to "showcase how good it is with doing that" since (a) people already see it's good and are hooked, (b) they don't want to stop the pace of changes and fall behind on features by focusing on stability and bug fixing.

They literally could use unlimited tokens and focus on both… it's telling that they cannot.

And they are TRYING to fix the bugs, they just keep failing over and over, so your reply is entirely incorrect.

Nice try though.

Re: Python 3.14 compiled to metal – no interpreter

#126

Post by coldtea »

LtWorf wrote: post #125
coldtea wrote: post #121

Earlier quoted context omitted.

They have little interest to "showcase how good it is with doing that" since (a) people already see it's good and are hooked, (b) they don't want to stop the pace of changes and fall behind on features by focusing on stability and bug fixing.

They literally could use unlimited tokens and focus on both… it's telling that they cannot. And they are TRYING to fix the bugs, they just keep failing over and over, so your reply is entirely incorrect. Nice try though.

>They literally could use unlimited tokens and focus on both… it's telling that they cannot.

If you ship updates fast, you can't just 'focus on both'. You focus on one or another, doesn't matter if you use "unlimited tokens", same way 9 pregnant women can't make a baby in a month.

>And they are TRYING to fix the bugs, they just keep failing over and over, so your reply is entirely incorrect.

That they "keep failing over and over" is a huge overstatement, it just has some bugs like other software has, so your point can be simply dismissed.

Re: Python 3.14 compiled to metal – no interpreter

#127

Post by LtWorf »

coldtea wrote: post #126
LtWorf wrote: post #125

Earlier quoted context omitted.

They literally could use unlimited tokens and focus on both… it's telling that they cannot. And they are TRYING to fix the bugs, they just keep failing over and over, so your reply is entirely incorrect. Nice try though.

> They literally could use unlimited tokens and focus on both… it's telling that they cannot. If you ship updates fast, you can't just 'focus on both'. You focus on one or another, doesn't matter if you use "unlimited tokens", same way 9 pregnant women can't make a baby in a month. > And they are TRYING to fix the bugs, they just keep failing over and over, so your reply is entirely incorrect. That they "keep failing…

> you can't just 'focus on both'

Can you explain why not? Just spin up another agent. 9 pregnant women can do 9 babies in 9 months.

This is a real question. I assure you that teams of more than 1 developer do exist, so I don't see why agents could not work on the same code.

> That they "keep failing over and over" is a huge overstatement

You call it an overstatement because of your religious beliefs. Unfortunately religious beliefs don't really change the fact that they keep failing in fixing their things.

https://www.youtube.com/watch?v=zfYsSFY4l18

Re: Python 3.14 compiled to metal – no interpreter

#128

Post by inigyou »

throw1234567891 wrote: post #102
nozzlegear wrote: post #59

Earlier quoted context omitted.

Who will pay if someone, somewhere is not passionate about it?

You can spin up a model locally and pay yourself. Who will maintain the project if the passionate sole maintainer burns out?

Which model works well?

Re: Python 3.14 compiled to metal – no interpreter

#129

Post by LtWorf »

worldsavior wrote: post #113
piloto_ciego wrote: post #98

Lol, all the people squawking about how this means nothing and this is a worthless project amuses me. A lot of people just don't see it yet. This is coming for literally everything and it is so exciting. The next decade is going to be awesome.

You can see it cause...you're a prophet right?

The man's called "blind pilot".

Re: Python 3.14 compiled to metal – no interpreter

#130

Post by anitil »

imtringued wrote: post #116
anitil wrote: post #86

Earlier quoted context omitted.

Your reply would have been much better without the first line [0] > Please don't comment on whether someone read an article. "Did you even read the article? It mentions that" can be shortened to "The article mentions that" [0] https://news.ycombinator.com/newsguidelines.html

No, it wouldn't, because he didn't actually read the readme which clearly states that they are still working on passing the CPython test suite and that 5x performance is an aspirational goal, not something they accomplished yet. >What is explicitly not done yet — this is the active roadmap, in order: >CPython test suite (cpython-full): the standing grind; failures are clustered and burned down per wave. >Stdlib build…

I noticed that it wasn't the best comment, I was only concerned with the tone, and I feel like dang has enough going on that we also need to help elevate the conversation. I admit there's some delicious irony in the accuser committing the same crime, but it doesn't improve the discussion to revel in that.
Post reply on HN