Ranking 6 Coding AIs Transforming Web Development in 2024

Поділитися
Вставка
  • Опубліковано 18 лис 2024

КОМЕНТАРІ • 50

  • @noriller
    @noriller 10 місяців тому +10

    Codeium for completions and the Phind (sometimes Perplexity) for searching.

    • @sligovolts
      @sligovolts 10 місяців тому +2

      Phind works beautifully, better than gpt4 for coding questions, that's for sure

  • @Crevulus
    @Crevulus 10 місяців тому +4

    Thanks for another year of great content, Jack. You're the senior/lead we all wish we had!

    • @jherr
      @jherr  10 місяців тому +2

      Thank you! I really appreciate the support.

  • @codernerd7076
    @codernerd7076 10 місяців тому +5

    Copilot got /workspace as well!

  • @w_x
    @w_x 10 місяців тому +5

    Phind pretty good as well for chat. I really like Cody for web for being able to understand a web repo quickly without having to open it in VSC

  • @avi7278
    @avi7278 10 місяців тому +11

    I'm still really underwhelmed by anything that is offered in vs code. My favorite by far is aider chat. It builds and entire map of your repo with ctags, and gives you the control to add exactly what files you want to context and uses a new unified diff editing structure backed by benchmarks which none of these other tools even come close to offering. It's completely terminal based and so I use it with neovim seamlessly. You can use it with gpt3.5 - 4turbo and local open source models (another advantage).

    • @RobertoFabrizi
      @RobertoFabrizi 10 місяців тому

      Did you manage to run aider via docker?

  • @user-he8qc4mr4i
    @user-he8qc4mr4i 10 місяців тому +2

    Thanks for sharing! Save me some time evaluating all of them

  • @xc13z829
    @xc13z829 10 місяців тому +5

    Jack, you missed Codeium!! I love their business model, and my colleagues and I prefer it to Copilot in many ways. Codeium is pretty dang good.

  • @prabhu4d
    @prabhu4d 8 місяців тому +1

    Always straight to the point in simple and fun way ❤

  • @fullstack-jack
    @fullstack-jack 10 місяців тому +4

    I believe Copilot has more context with @workspace agent.

  • @r-i-ch
    @r-i-ch 10 місяців тому

    Thank you so much for doing this comparison!!
    I do have to say that there *is* a difference between *bugs* and *poor practices* - AI helpers work well with occasional explanations and are good at working with a hammer. There are many surface connections in life that, have a far superior answers like glue, screws, nuts-and-bolts. But given enough nails and enough popsicle sticks, one *can* use a hammer to build the Taj Mahal.

  • @adlerspencer
    @adlerspencer 10 місяців тому

    Codeium(simple completion) + Pieces OS(Code Context and Chat)

  • @simpingsyndrome
    @simpingsyndrome 10 місяців тому +1

    i've use cody s for a couple months now, it's great and it's free

  • @evokelabs
    @evokelabs 10 місяців тому +1

    Did you try using the /workspace command at 5:05 ?

    • @jherr
      @jherr  10 місяців тому +1

      I did and, weirdly, it decided that the graphql schema file was relevant to the query but then it hallucinated the schema again.

  • @TonyManso
    @TonyManso 10 місяців тому +2

    3:42 Did your computer have at least 64gb of RAM, no other processes running, and have any other household electrical devices unplugged so they don't compete for electricity? This is JetBrains we're talking about after all 😛

  • @boogiman007
    @boogiman007 10 місяців тому

    My favorite AI coding tool is Jack Herrington

  • @VibronicCow
    @VibronicCow 10 місяців тому +1

    As other commenters have suggested, does copilot find the schema with /workspace? That would really put it a cut above the rest

    • @ableandrew
      @ableandrew 10 місяців тому

      copilot -insiders at least as of just before the end of 2023 /workspace feature fwiw

  • @MaksimPoshornyi
    @MaksimPoshornyi 9 місяців тому

    What about `Code GPT: Chat & AI Agents` extension for VScode ?

  • @blaqhakym
    @blaqhakym 10 місяців тому +1

    Hasn't anyone ever noticed how Jack and the popular American astrophysicist Neil deGrasse Tyson speak exactly alike? Please check one of his videos to confirm this. Two forces to reckon with in their respective chosen life paths. They also both look like they are in the same age bracket. Amazing!

    • @jherr
      @jherr  10 місяців тому

      Wow. Thanks! That's a really nice compliment.

  • @ricardogilsimoes
    @ricardogilsimoes 10 місяців тому +7

    I really wonder how Codeium fits in the ranking! I've tried Cody but I find Codeium slightly simpler.

    • @SkywalkerWroc
      @SkywalkerWroc 10 місяців тому +2

      Me as well! I found CodiumAI to be *the* best AI code assistant out there! Shame that it's missing from the comparison.

  • @manojpawar9088
    @manojpawar9088 10 місяців тому +1

    How about open source models like mistrel codellama ?

  • @afaceinacloud
    @afaceinacloud 10 місяців тому

    I believe copilot looked at all files in open tabs. Might be worth trying your gql test again with the schema open in a separate tab.

    • @afaceinacloud
      @afaceinacloud 10 місяців тому

      Looking at your other replies I see that it also hallucinated with @workspace so I guess this is unlikely to make a difference.

  • @artyomtaranenko2267
    @artyomtaranenko2267 10 місяців тому

    I test Codeium, but no clear answer with TS, but good autocomplete)

  • @editin232
    @editin232 10 місяців тому +1

    Should have tried Onboard AI.

  • @totomomo-ix3fq
    @totomomo-ix3fq 4 місяці тому +1

    wnat about codeium ?

    • @jherr
      @jherr  4 місяці тому

      Codeium is good. I've been using it recently, up until Copilot released their extensions stuff.

  • @RobertoFabrizi
    @RobertoFabrizi 10 місяців тому

    Cody doesn't work much does it? I asked how many public methods a class has, it replied with 6 (wrong total). In the list one of the 6 was private, I asked it if it was sure that it was really public, it said my mistake, it's private, there are 5 total. I tested again saying that "isn't ToString also private?" and he said you're absolutely right, it's also private, so there are 4 total.

    • @jherr
      @jherr  10 місяців тому +1

      Hmmm, that’s not the kind of question I would think to ask. But I would test it against a few AIs just to see if others get it right.

    • @RobertoFabrizi
      @RobertoFabrizi 10 місяців тому

      @@jherr if i may ask, why do you feel that these are questions you might not necessarily ask to such tools? If they can't tell a difference between a public and private method how can i expect them to find out more subtle bugs like the sorting in place? Plus the lack of conviction in their own replies is alarming, I simply asked if it was sure that tostring was really public and not private and it started hallucinating...

    • @jherr
      @jherr  10 місяців тому +1

      @@RobertoFabrizi Personally, I'm not looking at the AI as a source of definitive answers about something like the number of methods in a class. If I legitimately wanted to know the answer to that I would use a parser and look at the AST (and even then it's not so simple with inheritance).
      AIs produce a set of values with confidence scores. So with your question it probably generated several alternative answers to the number of methods both public and private and it had the highest confidence in what it presented as the answer. That's not a mechanism I would rely on to get "truth".
      Same reason that I would never take the code produced by an LLM at face value. I always inspect the output and make modifications

  • @nickwoodward819
    @nickwoodward819 10 місяців тому +1

    Haven't got round to watching yet, but thought tabnine was *terrible*. I used codium and find it slightly better. But not much

  • @TomNook.
    @TomNook. 10 місяців тому +1

    I'd like an offline only version

    • @coherentpanda7115
      @coherentpanda7115 10 місяців тому +2

      I don't think you understand how much computer power and storage is required for GPT- or similar model to run , even a single command.Unless you own a supercomputer in your basement, it's not happening

    • @sligovolts
      @sligovolts 10 місяців тому

      ​@@coherentpanda7115you can run text completion stuff on notebooks, it works and obviously it's not comparable to gpt4, but it's as good as gpt3.5

  • @khanra17
    @khanra17 6 місяців тому

    Why TF everyone include tabnine ?
    Tabnine is anything except AI.
    It has an early mover advantage but its suggestions are doog poop.
    It was a bad tool when no other tools were there and now it's worse.

  • @Norfeldt
    @Norfeldt 10 місяців тому

    @jackherrington did you write it like "@workspace write the graphql.."?
    This should search and find the needed context.

    • @jherr
      @jherr  10 місяців тому

      I did and it found the schema but then hallucinated the query.