Kodezi - Autocorrect for Programmers

Here is the relevant part that will answer everyone&#x27;s first question:<p>&quot;Your code is fully encrypted, never stored, and never leaves your machine.&quot;<p>However it also mentions &quot;Your data is completely secured at rest and in transit with encryption during analyzing and debugging&quot; which leads me to believe they don&#x27;t know what the prior statement means.<p><a href="https:&#x2F;&#x2F;kodezi.com&#x2F;security" rel="nofollow">https:&#x2F;&#x2F;kodezi.com&#x2F;security</a>

I&#x27;ve tried Copilot the last week and am severely underwhelmed. Many of suggestions don&#x27;t make any sense and it takes me more time to analyze and disregard the wrong ones than it saves me time. Most egregious though is that it suggests invalid code, i.e. code that can&#x27;t be compiled. For example it suggests a setter that doesn&#x27;t exist. I don&#x27;t know if I&#x27;m using it wrong but right now it&#x27;s not even worth the free trial for me.<p>I&#x27;m not sure if Kodezi is any better. But the page as so often doesn&#x27;t provide me with enough information without having to sign up and try it myself. Wanna know what &quot;Debug bugs&quot; actually looks like? Sure, watch this short styled up video which actually doesn&#x27;t show anything.<p>I found some information in the doscs <a href="https:&#x2F;&#x2F;docs.kodezi.com&#x2F;feature-guides&#x2F;debugging" rel="nofollow">https:&#x2F;&#x2F;docs.kodezi.com&#x2F;feature-guides&#x2F;debugging</a> but that&#x27;s a manual, not a proper feature presentation.

Did anyone notice that most (all?) of the logos underneath &quot;Supporting the top languages&quot; are in fact the logos of frontend&#x2F;JS frameworks, not languages?<p>Maybe this is far too pedantic, but I do wonder if the community&#x27;s over-indexing on frameworks to the point that they almost become languages is one of the deeper problems.

Obviously a lot of people have created&#x2F;will create wrappers for ChatGPT or DaVinci (or non OpenAI alternatives).<p>It&#x27;s hard to see how the integration layer adds any long term value. Although this is nicely presented etc. and I don&#x27;t mean to detract - just the entire class of tool.<p>I think the paradigm might eventually look like this: - you purchase your token directly from OpenAI - you do an oAuth flow to delegate access to many different wrapper apps (who maybe get a small referrer kickback from OpenAI)<p>I can certainly see myself subscribing at the source if I could take this token to the many wrapper-apps with trivial&#x2F;interchangeable commitment.<p>I don&#x27;t see myself individually subscribing to wrapper-layer apps.

I’m from the creed which does everything in eMacs and doesn’t even use a spell checker, and at the risk of being the old man that shouts at clouds, why would you want to compromise your ability to reason in this way?<p>Don’t do it! And don’t use a spell checker either! Get better and internalise more, you won’t get there with a crutch.

Founder of Kodezi here,<p>Answering some of the questions that was raised.<p>Our goal with Kodezi is to become a centralized development platform for developers to use regardless of their experience or skill level. We realized early on the amount of autocomplete clones, and our goal from day 1 was to create an autocorrect&#x2F;Grammarly-like approach to code debugging.<p>Original Post from 2021: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=29635354" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=29635354</a><p>In the next couple of months, we plan to release automated code debugging, merging, and automated PRs for Git, along with cloud integrations for Enterprises we are working with and a CLI for Kodezi. As well as a LLM for code debugging at scale.<p>Kodezi does not store your code; the data from file names we gather for our inference models use encryption.<p>Kodezi supports and debugs bugs of all nature, functional, syntax, logic, and more. We will have an overview of all types of bugs&#x2F;errors Kodezi has been trained on to give users a better idea of solving issues.<p>Kodezi uses large parameter language models trained on a collection of natural and programming languages from various open-source places, along with Open Source LLMs like Bloom and CodeGen. Kodezi has been training data from open-source repositories and StackOverflow data since 2019.<p>Code productivity and learning have been our goals since day 1; not an auto-completion tool that does not allow new programmers to learn.

Why doesn&#x27;t it run optimize on the code it generates?

Does anyone know if this uses OpenAI, or which model? OpenAI&#x27;s code-davinci-002 model is amazing and would be perfect for my startup but it only allows 10-20 requests per minute since it&#x27;s in beta.<p>Or if anyone has inside info on when that might come out of beta or a comparable alternative.<p>I wonder if it&#x27;s actually possible to fine tune text-davinci-003 to be better at programming.

The FAQ mentions that the main competitor GitHub copilot is only about completion, but it also have a few more features in common in the copilot lab extension.<p><a href="https:&#x2F;&#x2F;marketplace.visualstudio.com&#x2F;items?itemName=GitHub.copilot-labs" rel="nofollow">https:&#x2F;&#x2F;marketplace.visualstudio.com&#x2F;items?itemName=GitHub.c...</a>

I understand that someone has to be paid to generate AI, but one of the promises of programming of the last couple of years was that if you could afford a laptop and were smart enough you could contribute to software development by contributing to github and so forth. In practice I don&#x27;t know how much of that translates into practice (see AWS&#x2F;cloud&#x2F;hosting and so forth), but I don&#x27;t like this future where the only people who are able to program the machines are able to pay for an IDE that has a monthly or per usage cost structure.<p>The only people who get rich during a gold rush are the people that are selling the shovels. I think that people are tired of rewarding shovel sellers.