[HN Gopher] Show HN: Codeium - a free, fast AI codegen extension
___________________________________________________________________
Show HN: Codeium - a free, fast AI codegen extension
I'm Varun, CEO of Exafunction, and we just released Codeium to open
up access of generative AI to all developers for free. In the
spirit of Show HN, we created a playground version for anyone to
try this tech in the browser (click Try in Browser)! We have built
scalable, low-latency ML infra for many top AI companies in the
past, and we are excited to leverage that tech into a product that
we, as developers, would love. We hope that you do too, and we
would appreciate any feedback that this community has for us!
Author : varunkmohan
Score : 59 points
Date : 2022-12-06 19:27 UTC (3 hours ago)
(HTM) web link (www.codeium.com)
(TXT) w3m dump (www.codeium.com)
| monkeydust wrote:
| Any plans to allow fine-tuning on custom codebase?
| varunkmohan wrote:
| We are currently working on making suggestions more tailored to
| your codebase without having to persist / upload the codebase.
|
| We will have updates on this shortly!
| zanussbaum wrote:
| Has been a huge boost over using Copilot. I accidentally was
| using Copilot instead of Codeium and was confused why the
| generations took so long until I realized! Great product
| Micoloth wrote:
| I'll go ahead and ask the obvious question.. What's the
| difference with Copilot?
|
| In my exactly 3 minutes test, it did worse, even if only
| slightly.
|
| Right now it is free, but that won't last, right? Do i have to
| expect any shady data collection practices?
|
| More interestingly, how is this trained? Have you guys done your
| own finetuning of gpt3 or it's something completely different?
| varunkmohan wrote:
| Right now, we are providing a free alternative to Copilot and
| expanding the set of features we support. We are actively
| working on improving the quality of suggestions and would
| appreciate feedback.
|
| We guarantee that all users that join now will be able to use
| the product free forever. We explicitly allow users to opt out
| of sending data to us post inference. We believe we're in the
| early innings of code assistants and would like to democratize
| the technology so we don't have plans to monetize this tier of
| usage.
|
| The model is hosted internally and trained on public code. For
| more details on the specifics, please take a look at our FAQ
| page on the website.
| a1371 wrote:
| Say this on your landing page because it's a good
| differentiator, but it's not clear
| varunkmohan wrote:
| Thanks for the feedback!
| Micoloth wrote:
| Cool.. Thanks for your answer
|
| I have to say, in my quick tests completions do arrive
| slightly but noticeably faster than Copilot's.. Which is
| enough to make this interesting!
|
| Unless you are using a much smaller model, in which case it's
| too easy ahah.
|
| Thanks and good luck for your further plans, I'll keep trying
| this
| varunkmohan wrote:
| Thanks! We've made a lot of optimizations internally for
| latency. We've gotten a lot of feedback that it is faster
| than Copilot but obviously they operate at much larger
| scale.
| linuxdaemon wrote:
| I'm definitely for any alternative to an MS solution
| (especially one where I have to give them actual money to use
| it), but I had kind of the same experience. Not extensive
| testing, and I'm using it in PyCharm, so I don't know if that
| changes the behavior.
|
| The completion was weird. I tried to type "#Function to return
| the value passed". And it started to autocomplete with what I
| typed and what it was suggesting all jumbled up and completely
| unintelligible. Once I hit tab, it completed correctly, but it
| didn't make any sense until I hit tab, so I couldn't really see
| what I was completing until it was done.
|
| The more I played with it, I noticed it started to not actually
| suggest anything. But the codeium plugin is just showing a wait
| spinner in my status bar, so maybe it's getting pounded with HN
| people testing it right now.
| varunkmohan wrote:
| Interesting - would love if you could join our Discord
| (https://discord.gg/3XFf78nAx5) and we are happy to help
| figure out what's going on!
| culi wrote:
| > In my exactly 3 minutes test, it did worse, even if only
| slightly.
|
| What exactly does this mean?
| khou22 wrote:
| Been using this for the past couple of weeks and can attest it's
| been game changer for my productivity. Was skeptical at first,
| but I find myself less on Google search and more in flow. Thanks
| for giving it away for free
| culi wrote:
| Have you tried Copilot or CodeWhisperer previously?
| khou22 wrote:
| Yeah I used Copilot for a few weeks before since it was
| better known. Ended up cancelling my Copilot because I didn't
| notice a huge difference in quality/features and Codeium is
| free (primary motivation tbh)
| maille wrote:
| Alternatives to Copilot are more than welcomed. Do you plan to
| offer a plugin for MSVC ?
| varunkmohan wrote:
| We have gotten requests for more IDEs, and are actively working
| on creating support for them so that as many developers as
| possible can leverage this technology!
| waldenyan20 wrote:
| Amazingly fast! Would love to see the suggestions be a little
| better but it seems like a great team working on this.
| culi wrote:
| Cool. Well I guess until there's some community-driven open-
| source alternative I'll be rooting for y'all against Copilot and
| CodeWhisperer. Maybe you can pick up some of the Kite talent to
| join the effort
| varunkmohan wrote:
| Thanks for the support! We are actively looking to hire experts
| in program synthesis and ML infrastructure to help deliver this
| technology at scale
| swyx wrote:
| > scalable, low-latency ML infra
|
| I'm really really curious as to the technical details of getting
| the inferences cheap and fast enough to enable a copilot like
| experience when you're not GitHub with inifinity resources.
|
| Sam Altman has said that each chat in chatgpt is single digit
| cents per chat. GPT3 davinci is 0.02 per 1k tokens, not to
| mention the high latency. it'd be impossible to build "copilot
| for law" based on gpt3 because the UX wouldnt work with that
| latency or cost (you'd be running 100s of inferences if you count
| every debounced keystroke).
|
| What cost per user/per inference/per day (however you think about
| it) do you need to get this down to? and what order of magnitude
| speedups did you need to accomplish to get this done?
|
| (congrats btw, happy user here thanks to Prem)
| pqn wrote:
| Hey swyx :) Great question, we've got a blog post coming soon
| with some of these technical and other details... we've
| employed a lot of tricks here, debouncing included.
| swyx wrote:
| inject this straight into my veins
| mhuffman wrote:
| I have a ML infra that does between 1 million and 2 million
| inferences per day (granted it is not a chat bot or code
| generator, but it is legit ML inference in a similar mode) and
| it only cost $120 per month for the server (also runs multiple
| containers and is a web server), which mostly sits idle.
| fcoury wrote:
| I can't get it to work. Here's what I am getting:
| 2022/12/06 18:55:36 api_server_client.go:120: Completion error:
| rpc error: code = Unavailable desc = HTTP Logical service in
| fail-fast 2022-12-06 18:55:36.849 [INFO]: Completion
| request errored (236.63ms) 2022-12-06 18:55:36.849 [ERROR]:
| 14 UNAVAILABLE: HTTP Logical service in fail-fast
| varunkmohan wrote:
| Please join our Discord (https://discord.gg/3XFf78nAx5) and we
| are happy to help debug this for you!
| pmayrgundter wrote:
| Same.. web interface works but neither the plugin or discord
| link (here or on your site) are working for me.
|
| EDIT: clicking on the "return to vs code" link from your site
| was needed. now auth'd
| gigatexal wrote:
| I am dubious to use this at work since I can't be sure it won't
| send code from the codebase I am working on to the cloud. When
| something is free you're usually the product.
| varunkmohan wrote:
| We understand the concern! We describe our security policies in
| detail on our website, but we offer users the option to opt out
| from code snippet telemetry. This means after the inference, we
| do not store any code-based information on our end. We also
| know that you might not take our word for it, which is why we
| are working on getting SOC2 attestation for these policies.
|
| Also, to answer your pricing point, we are actively working on
| additional features beyond code completion. We want to try to
| make the code completion itself to be free, and definitely free
| forever for early users as a thank you for using Codeium from
| early on.
| gigatexal wrote:
| Well that's good. Let me pay for it, heck let me host it so I
| am sure. But getting audited is a good first step.
| varunkmohan wrote:
| We're actively thinking of ways where we host the service
| within a customer's tenant - more coming soon!
| gigatexal wrote:
| Amazing! Looking forward to it!
___________________________________________________________________
(page generated 2022-12-06 23:02 UTC)