How is THIS Coding Assistant FREE?
HTML-код
- Опубликовано: 14 май 2024
- Cody is Sourcegraph's AI coding assistant, and it has a couple of features that no other assistant has to make you a 10x developer. You can check it out here: srcgr.ph/ugzpQ
🛒 Gear Links 🛒
* 🍏💥 New MacBook Air M1 Deal: amzn.to/3S59ID8
* 💻🔄 Refurb MacBook Air M1 Deal: amzn.to/45K1Gmk
* 🎧⚡ Great 40Gbps T4 enclosure: amzn.to/3JNwBGW
* 🛠️🚀 My nvme ssd: amzn.to/3YLEySo
* 📦🎮 My gear: www.amazon.com/shop/alexziskind
🎥 Related Videos 🎥
🚀 LLMs: From Zero to Hero with M3 - • Zero to Hero LLMs with...
😲 MacBook Performance: Developer Shocked! - • Developer Shocked by m...
🤯 Mind-Blowing Machine Learning on Neural Engine - • INSANE Machine Learnin...
🍏 Apple Silicon: Who Needs It? - • Apple Silicon is back,...
🔗 AI for Coding Playlist: 📚 - • AI
#programming #ai #softwaredevelopment
- - - - - - - - -
❤️ SUBSCRIBE TO MY RUclips CHANNEL 📺
Click here to subscribe: www.youtube.com/@azisk?sub_co...
- - - - - - - - -
📱LET'S CONNECT ON SOCIAL MEDIA
ALEX ON TWITTER: / digitalix
CODY ON TWITTER: / sourcegraphcody 
Наука
My concern is that in order for the suggestions to be presented, your code has to be sent via the plug-in to Cody/CoPilot and “fed” to the LLM on their servers. How do we know that these services aren’t stockpiling users’ code that may one day be divulged to the internet due to a security leak?
Very important question. Maybe that's why the feature, running your own LLM, is important.
This is literally the case for every cloud LLM plugin in editors right now, it's honestly not that big of a deal. If one does care, they can link a local LLM.
I’ve been joking that I don’t upload to GitHub cause they train AI on our code… but now this joke isn’t fun anymore
(also) here applies the well-known: "If something is free, you are the product."
This is specially holds more true for young and hungry startups.
Hey man! I'm a senior in computer science. I enjoy your content so much. I really look forward to you making videos on Apple's MLX framework. I have a 14" M2 Max 30 core GPU and I'd really like to see how much elbow grease it could do vs other Macs.
It looks very promising. Testing it right now. Thanks for sharing it!
I have been using a plug-in called pieces that does snippet storage, but they also have a chat feature where u can use cloud or local LLMs along with adding portions of your code to the model’s sight
same here
@@filmyguyyt Thanks for the support :)
That sounds awesome.
I’m concerned about privacy when Cody “addresses” my entire codebase.
Yeah, Alex probably gave up his entire work to Cody, OpenAI etc. by uploading it…
Alex did mention that his projects are open source.
@@jasonlitsonfair enough. I still don’t don’t like the whole development (data is money)
@@jasonlitson open source projects have different licenses. Are those services adhering to the license of the project?
I don't mind with open source but yeah what if I want to try it at work
At the rate we are going, I think it will only be a few years to where Local LLMs will be "good" enough coding assistants
(hopefully that will end subscription costs 🤷🏼♂)
On my 64GB M2 Max MBP running phind-codellama:34b already gives me performance comparable to GPT-3.5 or even better, but maybe not on the level of GPT-4 just yet. Imo it will take maybe 6 months to be able to run on local hardware. Imo a 96GB or 128GB m1 or m2 ultra should be more than enough to run this. String this with a git hub project that creates a webui on local host, host that on ngrok, and you can use it anywhere. I have done exactly that and it's spectacular. Better to run LLMs locally for confidential code. I used the ollama git hub project btw, which also has projects linked in the description.
@SahilP2648 Have you tried deploying other LLMs on-premises, or even fine-tuning them? I'm thinking about buying a 96GB m2 max, I want to try fine-tuning some LLMs locally, and now this mbp has some deals and it's very portable (which I value a lot)
@@user-ob7fd8hv4t I haven't tried fine tuning as I don't have the need to and I am not an ML researcher (Android app developer). But it might be faster on a 4090. The main problem is VRAM which Macs have plenty of, if you can shell money. I have tried plenty of models and for my purposes I can get away with a simple system prompt change. Inference speed is quite good too.
But need much powerful machines thats the issue
@@user-ob7fd8hv4t Finetuning requires about 5-10x the vram than running it. Just keep that in mind
I am glad that I subscribed to you.
Thanks for subbing!
You can actually correct to local llm already. I connected to the code llama and it works well
In theory, if your local LLM application presents an open ai compatible api, you could that in combination with something like cody. Suppose even if it was locked down, you could edit your hosts file and point open api servers to your local llm.
good idea with the host file! :) of course this only works if the requests do not get proxied through some cody endpoint first (i dont know if they are)
Now that is some original thinking 🙃
I wouldn’t bet that they will do local LLMs to the free tier because it may discourage people from purchasing a premium tier if they can just run it using their own model locally. The free tier gives you a “taste” and the artificial limit is to encourage you to buy the premium tier. I do like that you can try before you buy
Sounds like we need an open-source "Cody" that runs on local LLMs. That would be awesome.
Pieces for Developers does this for free!
Can you make a video comparing the 18GB M3 Pro MacBook Pro to the 36GB M3 Pro MacBook Pro with regards to developers' needs, also including VM?
Any idea what LLM they are using? I can't find any information about it on their website.
Great video as always !
thanks 🙏
You can compare MacBook air M1 8gb RAM VS MacBook pro M3 18gb RAM, I want to identify if it is really worth the upgrade
They also support Mixtral 8x7b
you are a man from heaven 😮
that was my concern bro
The new 14th Gen Intel processors for laptops just got released. Hope to see you get one🙋
Always love to watch your videos.... Love from India
Thanks a ton
@@AZisk most welcome
I've used it. It's great.
What max are you using in the video?
Wish you addressed this rate limit more
The UI is a bit scattered. Claude 2 in the free version, for others have to go pro. If you index your project, it gets uploaded (not sure what the other full-project coding AIs do there).
Actually, without that video, the UI would have been quite confusing. Like choosing LLM + indexing project are almost impossible to find.
Pro is free to 2024, so what are you talking about?
@@user-gy1dh3kq9p Wasn't obvious, thx, indeed works until end of january!
Hmm, I'm on code pro and intellij, but can't see any place to change llm
is there a way to run local llm with codey? a work around?
What do you think about codeium?
Liking this video so he can buy some not so cheap car
Thanks for the like! I don't need an expensive car, just need to save for the next MacBook so I can review it here.
Lmao
I am sure you are already aware, but there is infect a "version" of cody that can use local LLM, it's called collama.
To be honest, I have not compared it to cody, but at a basic level it seems ok.
Does a viable local version of similar technology exist?
Why does this cost money, it is just a extension for vscode that calls some apis (or are they actually paying for the API consumption, I guess that would explain the rate limits in the free version)?
How is copilot free for open source contributors? Is that a GitHub program?
Great video, local llm ftw!
Thanks!
do you think a i7 1355 U with 32GB RAM and 1 TB laptop is fine for learning these AI and LLM stuffs or a Macbook pro is better.
And NVIDIA RX 3060 family or higher with 8 / 12 GB RAM?
hello, i am facing a slight electric shock like sensation on the top of lid of MacBook while charging with the given power adaptor itself and tried this in multiple sockets and outlets still the same, people over internet are saying this as tingling and it is normal, but it is causing discomfort to use the machine while charging, my question is, is everyone who have 2 prongs adaptor faces this issue in countries where grounding is done with a third prong ?
It is ok
Here is an interesting idea. I wonder if you can train Cody on specific engines. For instance Train Cody on the Unreal engine. Hmmmm
Any thoughts on how Sourcegraph AI's Cody compares to Perplexity AI or CodiumAI?
why didn't you type that /smell over you code base? ;-)
As a rule: if it's free, you are the product.
I guess in this case you pay with your code and they use it to further train their llms
And do what else with it? How do you know it won't wind up in someone else's suggestions verbatim?
@@EdKolisthere is nothing wrong with that, even when you are using copilot/chatgpt, you are using someone elses code, the problem is when your private info like api keys end up in their llms
@@maevwat what if your code contains trade secrets?
If I'm just starting off on learning programming, is it worth it to install something like this? Or is it more detrimental to learning to have help like this?
It can allow you to learrn faster so i think its worth.
this needs to be part of your learning now
Thanks for the answer! @@AZisk
That would be neat. Thank you.@@VforVanish
I'm not a coder by any means, but I've written apps for myself several times by searching through wiki help articles and example scripts etc. Similar concept, I didn't go to school or learn anything crazy, just got the feel for it enough to build something simple and that alone was enough to help me understand a little when looking at stuff like this.
No worries, you pay for it with your data.
thumbnail goes crazy
is that good or bad?
@@AZisk excellent in my opinion. love your videos man!
thanks 🙏
So how do we know cody is not saving (stealing) our code somewhere else ? I would likely be fired if my boss knew I was using unauthorized coding assistants.
pieces is better yk i think
Why should they implement local models? They want to make money with it.
Checkout codeium next!
my favorite one is CODEIUM AI :)
vs cody, which one is better ?
@@freqtion codeium
uh oh. uh oh Alex? yes Alex. Alex? uh oh Alex. is that clippy Alex?
You had me at free
One indexation and LLM has all your logic, passwords, settings, database names, structures etc which are stored in project. Too risky to run. Especially on commercial projects.
You best be better than the "coding assistant" else you are done in a coding career. Any idiot can just use the "coding assistant". The good news is, the coding assistants still make wrong/bad/crap code, full of errors and implementations that may work, but only later you realize they don't work the right way.
Cody is now Generally Available, and Cody Pro is free until February 2024.
It's free because you are the product.
Only totally free until February 2024, then $9/month for unlimited completions over 500 completions in it's free form.
Yeah I get where the hype is coming from, I'm pretty sure Cody will dethrone Roman at Wrestlemania.
It’s free because your code is their code 😆
Free
tier
0 / 500
Autocomplete suggestions
this month
0 / 20
Chat messages and commands
this month
Have to say DuetAI made me jump ship from CoPilot.
Can you tell me why? Duet AI seems to be very unaware of my code , It seems i have to give it alot of context for it spit something good back
For the ones that don't know, IT IS NOT AWARE of your ENTIRE code base. Nope
It is just vector embeddings, to form a context when you ask it something, then it adds the context to your query before sending it to the LLM.
Nothing crazy
for a LLM to be aware of your entire code base, you need to finetune it! If Cody offers a way to finetune an LLM on your repo, then it will be true, it will know everything about your repo
Claude2 has 128k context, so..
GP4 Turbo is 128 and Claude2 is 100. If you want better, Claude 2.1 is 200. @@leoingson
Why this guy is weirdly attractive🥰
Weakest point. It is not available in visual studio. Since I use vs rather than vs code this is a no go for me. Shame would have liked to try it
I expect Googles upcoming coding assistent to be the best and COMPLETELY free!
They’ve already announced that it will cost $19 a month and you can only sign up annually.
Why would it be free?
I checked Bard (using Gemini Pro now) against ChatGPT 4 and Bard made some very incorrect statements (no pun intended) regarding C++ code I pasted. Very incorrect and even fundamentally wrong stuff that even novice programmers will see.
@@sushicommander Ok, disappointing! And even more expensive than CoPilot??!? Do you have a link?
@@JuanFmTech The rest of the dev tools are also free and if it runs locally, I see no reason to charge for it!
moar! lol🙀
500 Autocompletions per month, so it's not technically free, since those can all be used in a day, nice video tho!
Codeium
i thought codeium was better
Not free anymore. 500 Autocompletions per month on free tier, then 9$/month
did you say it’s not free and free tier in the same sentence? 😆
@@AZisk ok, "not Unlimited anymore" ...
i am notorious for stinky code
me too :)
nothing is free , they use your coding data to train their models :)
New sub here and like your video but i dont like how you all the time do these zooming in effect like at min 1.3 and jumping frames all the time... These effect give me headache and i start to lose focus on the video and lose interest to learn something from it.. could you please stop doing that in future videos ?
Have fun with all your broken code that the AI hallucinated was "secure" and "optimal".
if one has fun coding, one has fun reviewing code. always review your code and ai generated code
Free but limited
You should use an LLM to come up with a video title that isn’t so cringe and clickbaity. Such a RUclips cliché.
Ai is a tool to teach you code with no teacher available. If you know code, don’t use ai?
your video is TOO LOUD
I don't like it. Too black-box.
*\• I believe we are meant to be like Jesus in our hearts and not in our flesh. But be careful of AI, for it knows only things of the flesh which are our fleshly desires and cannot comprehend things of the spirit such as true love and eternal joy that comes from obeying God's Word. Man is a spirit and has a soul but lives in a body which is flesh. When you go to bed it is the flesh that sleeps, but your spirit never sleeps and that is why you have dreams, unless you have died in peace physically. More so, true love that endures and last is a thing of the heart. When I say 'heart', I mean 'spirit'. But fake love, pretentious love, love with expectations, love for classic reasons, love for material reasons and love for selfish reasons those are things of the flesh. In the beginning God said let us make man in our own image, according to our likeness. Take note, God is Spirit and God is Love. As Love He is the source of it. We also know that God is Omnipotent, for He creates out of nothing and He has no beginning and has no end. That means, our love is but a shadow of God's Love. True love looks around to see who is in need of your help, your smile, your possessions, your money, your strength, your quality time. Love forgives and forgets. Love wants for others what it wants for itself. However, true love works in conjunction with other spiritual forces such as patience and faith - in the finished work of our Lord and Savior, Jesus Christ, rather than in what man has done such as science, technology and organizations which won't last forever. To avoid sin and error which leads to the death of your body and your spirit-soul in hell fire (second death), you must make God's Word the standard for your life, not AI. If not, God will let you face AI on your own (with your own strength) and it will cast the truth down to the ground, it will be the cause of so much destruction like never seen before, it will deceive many and take many captive in order to enslave them into worshipping it and abiding in lawlessness. We can only destroy ourselves but with God all things are possible. God knows us better because He is our Creater and He knows our beginning and our end. The prove text can be found in the book of John 5:31-44, 2 Thessalonians 2:1-12, Daniel 2, Daniel 7-9, Revelation 13-15, Matthew 24-25 and Luke 21.
*HOW TO MAKE GOD'S WORD THE STANDARD FOR YOUR LIFE?*
You must read your Bible slowly, attentively and repeatedly, having this in mind that Christianity is not a religion but a Love relationship. It is measured by the love you have for God and the love you have for your neighbor. Matthew 5:13 says, "You are the salt of the earth; but if the salt loses its flavor, how shall it be seasoned? It is then good for nothing but to be thrown out and trampled underfoot by men." Our spirits can only be purified while in the body (while on earth) but after death anything unpurified (unclean) cannot enter Heaven Gates. Blessed are the pure in heart, for they shall see God (Matthew 5:8). No one in his right mind can risk or even bare to put anything rotten into his body nor put the rotten thing closer to the those which are not rotten. Sin makes the heart unclean but you can ask God to forgive you, to save your soul, to cleanse you of your sin, to purify your heart by the blood of His Son, our Lord and Savior, Jesus Christ which He shed here on earth - "But He was wounded for our transgressions, He was bruised for our iniquities; the chastisement for our peace was upon Him, and by His stripes we are healed", Isaiah 53:5. Meditation in the Word of God is a visit to God because God is in His Word. We know God through His Word because the Word He speaks represent His heart's desires. Meditation is a thing of the heart, not a thing of the mind. Thinking is lower level while meditation is upper level. You think of your problems, your troubles but inorder to meditate, you must let go of your own will, your own desires, your own ways and let the Word you read prevail over thinking process by thinking of it more and more, until the Word gets into your blood and gains supremacy over you. That is when meditation comes - naturally without forcing yourself, turning the Word over and over in your heart. You can be having a conversation with someone while meditating in your heart - saying 'Thank you, Jesus...' over and over in your heart. But it is hard to meditate when you haven't let go of offence and past hurts. Your pain of the past, leave it for God, don't worry yourself, Jesus is alive, you can face tomorrow, He understands what you are passing through today. Begin to meditate on this prayer day and night (in all that you do), "Lord take more of me and give me more of you. Give me more of your holiness, faithfulness, obedience, self-control, purity, humility, love, goodness, kindness, joy, patience, forgiveness, wisdom, understanding, calmness, perseverance... Make me a channel of shinning light where there is darkness, a channel of pardon where there is injury, a channel of love where there is hatred, a channel of humility where there is pride..." The Word of God becomes a part of us by meditation, not by saying words but spirit prayer (prayer from the heart). When the Word becomes a part of you, it will by its very nature influence your conduct and behavior. Your bad habits, you will no longer have the urge to do them. You will think differently, dream differently, act differently and talk differently - if something does not qualify for meditation, it does not qualify for conversation.
*THE BATTLE BETWEEN LIGHT AND DARKNESS (GOOD AND EVIL)*
Heaven is God's throne and the dwelling place for God's angels and the saints. Hell was meant for the devil (satan) and the fallen angels. Those who torture the souls in hell are demons (unclean spirits). Man's spirit is a free moral agent. You can either yield yourself to God or to the devil because God has given us discretion. If one thinks he possesses only his own spirit, he is lying to himself and he is already in the dark. God is light while the devil is darkness. Light (Holy Spirit) and darkness (evil spirit) cannot stay together in a man's body. God is Love (Love is light) and where there is no love is hell, just as where there is no light is darkness. The one you yield yourself to, you will get his reward. The reward of righteousness to man's spirit is life (abundant life) and the reward of sin to man's spirit is death. Sin and satan are one and the same. Whatever sin can cause, satan also can cause. Sin is what gives the devil dominion or power over man's spirit. When God's Word becomes a part of you, sin power over you is broken, you become the righteousness of God through Christ Jesus. Where Jesus is, you are and when He went (to the Father), you went. In the book of John 8:42-47, Jesus said to them, “If God were your Father, you would love Me, for I proceeded forth and came from God; nor have I come of Myself, but He sent Me. Why do you not understand My speech? Because you are not able to listen to My word. You are of your father the devil, and the desires of your father you want to do. He was a murderer from the beginning, and does not stand in the truth, because there is no truth in him. When he speaks a lie, he speaks from his own resources, for he is a liar and the father of it. Which of you convicts Me of sin? And if I tell the truth, why do you not believe Me? He who is of God hears God’s words; therefore you do not hear, because you are not of God.” May God bless His Word in the midst of our hearts. Glory and honour be to God our Father, our Lord and Savior Jesus Christ and our Helper the Holy Spirit. Watch and pray!... Thank you for your time and may God bless you as you share this message with others.
500 auto suggestions per month 👎
How is it free?! It lets you ask it something like 10-20 questions a MONTH, and some stupid low number of completions. You have to pay to just use the thing. What a rip off.