Skip navigation
Using LLaMA 3 70B on GroqInc to instantly refactor and document code.
0:00 / 0:21

Using LLaMA 3 70B on GroqInc to instantly refactor and document code.

Matt Shumer

@mattshumer_404K followers

Visit on X
2,032 likesDownloadOriginal post

442,864 views

Using LLaMA 3 70B on GroqInc to instantly refactor and document code. The implications for software engineering are wild. Gone are the days of waiting on an LLM for suggestions or code changes. Now, it's an instant feedback loop. Demo link in the comments:

10 Comments

Comments from the original post on X (Twitter)

  • Matt Shumer's profile picture

    @mattshumer_

    Try it here:

    167 likes

  • Andrej Karpathy's profile picture

    @karpathy

    @GroqInc ugh kids these days! back in my days we used to watch the tokens stream one at a time and wait for the output.

    2,411 likes

  • Matt Shumer's profile picture

    @mattshumer_

    @GroqInc Dude…. big fan. Your character-level GPT models were how I initially got into training models

    144 likes

  • Gillinghammer's profile picture

    @gillinghammer

    @GroqInc slap it in a VSCode extension immediately

    31 likes

  • Matt Shumer's profile picture

    @mattshumer_

    @GroqInc I'm sure the @cursor_ai team is thinking about something similar

    46 likes

  • Ciprian Cîmpan 🌶️'s profile picture

    @devnulli

    70B + @GroqInc = absolutely awesome combo 💙 the only downside is that they don't let us pay yet (free tier is throttled🥲)

    27 likes

  • Haider.'s profile picture

    @slow_developer

    @GroqInc Groq is getting rightly attention after the Meta Llama 3.

    11 likes

  • Jon Mitchell's profile picture

    @mitchelljon

    @GroqInc Groq speed + 1M context + agents = 🔥

    4 likes

  • Andrew Sperazza 🇺🇸's profile picture

    @sperazza

    @GroqInc @GrocInc is highly under-rated.

    4 likes

  • @asyncze's profile picture

    @asyncze

    @GroqInc 👀

    2 likes