[HN Gopher] Build your own GitHub Copilot with Salesforce CodeGe...
       ___________________________________________________________________
        
       Build your own GitHub Copilot with Salesforce CodeGen AI [video]
        
       Author : amrrs
       Score  : 57 points
       Date   : 2022-06-30 15:58 UTC (7 hours ago)
        
 (HTM) web link (www.youtube.com)
 (TXT) w3m dump (www.youtube.com)
        
       | arriu wrote:
       | It seems people are frustrated with GitHub's CoPilot pricing
       | model
        
       | zora_goron wrote:
       | I implemented a "mini" version of Copilot using EleutherAl GPT-
       | Neo-2.7B and HuggingFace model hub and wrote a wrapper to use in
       | emacs -- https://github.com/samrawal/emacs-secondmate
       | 
       | It's much more rudimentary compared to Copilot, but it's fun to
       | play around with, and it can be run completely locally (after the
       | model is downloaded). Plus it runs using a simple Flask local
       | server, so it can be easily extended to other text editors.
        
       | bigChris wrote:
       | Copilot works well for human readable languages languages like
       | python; JavaScript(web framework)
       | 
       | If I start coding in Haskell, C and Objective-c to hack my
       | iPhone. Guess what. Copilot stops helping or just recommends the
       | same arbitrary genetic ideas I can google myself.
       | 
       | For python and JavaScript? It seems to do really well at
       | predicting the next function and ideas.
        
         | agluszak wrote:
         | I can say that it works very well with Rust
        
         | petercooper wrote:
         | It's good, but as a Rubyist, I find it generally picks the most
         | common solution to problems rather than the best one. Get it to
         | tally the contents of a hash, for example, and it doesn't reach
         | for Hash#tally at all, but the long "manual" way of doing it.
         | So it makes me wonder if I'm encountering a Gell-Mann type
         | effect with languages I'm less familiar with..
        
         | capableweb wrote:
         | Surprisingly, Copilot worked well with Clojure when I tried it.
         | I don't know if it's because most lisps are very similar, so it
         | borrows a lot of code from other languages while just changing
         | the variable names, but seemed to have worked fine.
         | 
         | More advanced ideas obviously resulted in trash code or
         | sometimes slightly broken one, but for simple stuff and
         | boilerplate editing, it did well.
        
           | eurasiantiger wrote:
           | Just like having the copilot fly the plane ;)
        
         | picozeta wrote:
         | Could it be that it just hadn't seen enough (Haskell) training
         | data. The amount of code in it is tiny compared to Python,
         | JavaScript and Java.
         | 
         | So even the AI struggles to learn it. :p
        
         | alexott wrote:
         | Go worked quite well...
        
         | kache_ wrote:
         | it's over for esoteric functional programming languages
        
       | enijkamp wrote:
       | For our >350M models, here is an example of how to load these
       | within Colab:
       | 
       | https://colab.research.google.com/drive/11YU00W-JLNXn-3YckJG...
       | 
       | This little hack will force tensor alloc on GPU instead of CPU
       | mem.
        
         | amrrs wrote:
         | Wow this is amazing. Sorry for a dumb question, will it work
         | any such LLMs or only in Codegen's case?
        
       ___________________________________________________________________
       (page generated 2022-06-30 23:01 UTC)