TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

StableCode

305 pointsby kpozinalmost 2 years ago

18 comments

Uptrendaalmost 2 years ago
&gt; People of every background will soon be able to create code to solve their everyday problems and improve their lives using AI, and we’d like to help make this happen<p>Yeah, this is not going to happen. Anyone who has ever tried to gather requirements for software knows that users don&#x27;t know what they want (clients especially lmao.) The language they use won&#x27;t be detailed enough to create anything meaningful. Do you know what language would be? Code... Unironically, the best language for software isn&#x27;t English. It&#x27;s code. Should you specify what you want in enough detail for it to be meaningful suddenly you&#x27;re doing something quite peculiar. Where have I heard it before? Oh yeah, you&#x27;re writing code.<p>These tools are all annoying AF. Developers don&#x27;t need half-baked hints to write basic statements and regular people don&#x27;t have the skills to hobble together whatever permutations these things spit out. Which rather begs the question: who the hell is the audience for this?
评论 #37057028 未加载
评论 #37057584 未加载
评论 #37057680 未加载
评论 #37057387 未加载
评论 #37058109 未加载
评论 #37057019 未加载
评论 #37060285 未加载
评论 #37069636 未加载
评论 #37071027 未加载
评论 #37058145 未加载
评论 #37062292 未加载
评论 #37058082 未加载
评论 #37066639 未加载
gaogaoalmost 2 years ago
Its metrics on HumanEval seem not particularly good (26.89 Pass@1 for it vs. 61.64 for PanGu-Coder2 15b). Is it targeting a very specific latency for responses? I&#x27;d think a 15b quantization should run fast enough for most use cases? Even phi-1 1.3B has better performance at 50.6.
dragonwriteralmost 2 years ago
&gt; People of every background will soon be able to create code to solve their everyday problems and improve their lives using AI, and we’d like to help make this happen<p>Just like everytime people hyping a technology have said this with something else where “AI” is but otherwise an identical claim, no, it didn’t happen last time, its not happening this time, and there’s a pretty good chance its not happening next time, either.
runakoalmost 2 years ago
Is this a &quot;product&quot; that one could install and use or a model that one should expect an OEM to integrate into a product before programmers can use it? I&#x27;m asking because I don&#x27;t see any links that would help me figure out how to try it out.
评论 #37053297 未加载
评论 #37053757 未加载
评论 #37053567 未加载
cutleralmost 2 years ago
Yet another site whose data privacy policy amounts to nothing more than an Accept button. Refuse to use such sites.
评论 #37055155 未加载
评论 #37056648 未加载
sebzim4500almost 2 years ago
Hard to believe it can work that well when it only has 3B parameters, but I&#x27;d love to be proven wrong.
评论 #37053286 未加载
评论 #37053773 未加载
评论 #37055173 未加载
评论 #37053735 未加载
评论 #37053075 未加载
3rd3almost 2 years ago
How does it compare to GitHub Copilot?
评论 #37054931 未加载
评论 #37054908 未加载
评论 #37055584 未加载
RomanPushkinalmost 2 years ago
Is it good at algos?<p>From interviews:<p>Implement queue that supports three methods:<p>* push<p>* pop<p>* peek(i)<p>peek returns element by its index. All three methods should have O(1) complexity [write code in Ruby].<p>ChatGPT wasn&#x27;t able to solve that last time I tried <a href="https:&#x2F;&#x2F;twitter.com&#x2F;romanpushkin&#x2F;status&#x2F;1617037136364199938" rel="nofollow noreferrer">https:&#x2F;&#x2F;twitter.com&#x2F;romanpushkin&#x2F;status&#x2F;1617037136364199938</a>
评论 #37057076 未加载
评论 #37063618 未加载
评论 #37056790 未加载
thewataccountalmost 2 years ago
I can&#x27;t seem to find a demo, if anyone has a chance to test it, how does it compare to replit and wizardcoder?
评论 #37053487 未加载
MyAccountYoalmost 2 years ago
I have thought about how these tools can be useful quite a lot. I have a prompt I can feed chat gpt and it will create whole feature &quot;skeletons&quot; with my naming rules and architecture quirks. Taking a lot of time from getting started when building something new. But with chat it is still too inconvenient, having something like this integrated in the ide via a script would he more convenient but still a very specific use case.<p>I think what I want is this idea of &quot;code completion&quot; but not for writing the methods, which is the easy part. Instead the tool should structure classes and packages and modules and naming and suggest better ways to write certain things.
smcleodalmost 2 years ago
If I’m reading this correctly this could be an open source model that may compete with the likes of copilot?<p>That is something I’d be very interested in if they can get the compute requirements down to those of say a standard 13B model. Then I could fine tune (correct term?) it on my offline data and hook it into something like fauxpilot and my IDE.<p>I had a look at some of the recent code models (wizardcoder,strider etc) but it seemed that you need a really large model to be any good and quite a few of them were trying specifically for python.
评论 #37073913 未加载
jaimani_langooalmost 2 years ago
AI Cannot magically read minds. Having said that It would be nicer to have complete solutions rather than code hints. Imagine having to write a detailed prompt rather than choosing a prediction. Something like : &quot;Write a React&#x2F;Node JS app that has authentication and a home page&quot; and the AI model give you a complete project as the output. It would be great if it generates deterministic output for the Prompt. AI can really help increase the productivity of Programmers.
whimsicalismalmost 2 years ago
&gt; ~120,000 code instruction&#x2F;response pairs in Alpaca format were trained on the base model to achieve this result.<p>Very curious where they are getting this data from. In other open source papers, usually this comes from a GPT-4 output, but presumably Stability would not do that?
rvzalmost 2 years ago
Either way, the race to zero has been further accelerated.<p>Stability AI, Apple, Meta, etc are clearly at the finish line putting pressure on cloud only AI models and cannot raise prices or compete with free.
评论 #37055098 未加载
评论 #37053386 未加载
评论 #37052974 未加载
评论 #37057209 未加载
ethereal_aialmost 2 years ago
As a user who cares more about the product, how does it compare to the gpt-4 code capability? gpt-4 is good enough for me, if it works better than gpt-4 I would love to try it!
nwolialmost 2 years ago
I love stability AI
monlockandkeyalmost 2 years ago
Any performance metrics?
eduardocrsalmost 2 years ago
&quot;People will never ...&quot;<p>Ai: &quot;Hold my beer&quot;.