I’m a software engineer at a startup with impossible deadlines - I’ve used GPT4 for months to generate huge amounts app/server code, and much like your IDE, once you learn to use these tools you don’t want to go back to the days without it.
Speed
- Bard is very fast- similar to GPT 3.5 Turbo
- You need to multitask two GPT4 instances side by side to compensate for how slow GPT4 can be
Reliability
- Bard lies and makes up fake API calls more than GPT4
UI
- Bard UI is garbage - You have to keep manually scrolling down the chat window, and for some reason the largest button on the page is “stop” (???)
- You can tell Bard to modify its response to be longer/shorter and a few other options - I thought this would be useful, but it never ended up helping
Memory
- Bard has really short memory - Forgets details from last response!
- GPT4 memory is also unreliable, any details that are important you have to repeat
Intelligence
- GPT4 is objectively smarter
Internet Search
- GPT4 Internet search is garbage
- Bard has “Verify with Google” - I had high hopes for this, but never actually had a use for it
Willingness to give full code
- GPT4 is bad, but Bard is worse. Both need to be begged/threatened to return more than 100 lines of directly paste-able code.
Generating Useful Code
- Bard can give more concise medium complexity functions
Adding tougher features
- Bard hallucinates and lies
Dealing with lies
- When you tell GPT something doesn’t work, GPT will try something else
- When you tell Bard something doesn’t work, Bard will lie, claim to fix it, then give back the same code
Following Instructions
- GPT4 sometimes doesn’t follow instructions, but improving the prompt will fix that. Bard will happily ignore instructions, as clear as they may be.
Summary:
- GPT4 is still objectively better than Bard. Quite frankly, the prompts Bard couldn’t handle, GPT3.5 could.
- The cons of GPT can be worked around, but for Bard, it’s almost faster to do it yourself. Unless Bard was used like Copilot for short 1-2 lines of autocomplete, I wouldn’t trust it.
PS: If you’re not using AI yet for development, I highly recommend it - It’s like using an IDE instead of Notepad. AI can easily 2-3x your output, but you have to learn how it works so you can prompt it correctly, and you have be good at fixing its mistakes.
I still can’t understand why Google keeps hyping up Bard and then releasing it at a poor state just to ruin their reputation. First, we had:
-
Bard 1, which was hyped up to be the ChatGPT successor. It turned out to be really bad.
-
Bard 2.0, a massive update that was hyped up to make Bard so much better. It turned out to still be pretty bad (but in fairness it was a minor improvement).
-
Google Gemini, their massive response to GPT 4 that was, on paper, the best LLM in the world. They finally integrated it into Bard last month and… It’s still not great. I could not tell an immediate difference between this and the old Bard. Oh, and the videos they used to advertise Gemini Ultra were fake.
I’m not going to armchair analyze a hugely successful company, but from my point of view it really shows how mismanaged Google has been in the past decade. Failed projects upon cancelled projects upon increasingly frustrated employees.
/rant. Anyways, you should consider using Preplexity if you want something with search capabilities, I’ve had decent success there. Claude is also significantly better than Bard, but they made free usage very limited lately. Might be a good option if you’re willing to pay.
-
I’ve also given bing gpt4 some coding related stuff and for first year comp sci, it can pretty much do it. Anything beyond, you will need very specific instructions, at that point, you can probably code it yourself. If you aren’t specific, it will give you something entirely wrong, claim it did your prompt, gives lots of errors many of the time. You have to baby walk it a lot of the time.
Additionally, it feels way more restrictive than a few months back. Seems like it gives you generic prompts and not even try to spin it up a little.
I’m a software engineer […]
No… No, you’re not …
You are that guy who takes 50 guesses at the easy trivial pursuit questions and then claims you knew the answer all along.
https://github.com/dginovker, https://gitlab.com/dginovker
@me bro. I’ve been writing open source software for 5 years before GPT came along. Keep up with the tooling. I recommend you try it before you knock it.
I have 15+ years of experience being a software engineer and now I’m making a mid-six-figure income by going into companies who staff their “engineering department” with people who have five years or less of experience and cannot write a line of code without internet access to save their lives. So by all means go ahead and continue down the road you are going. We thought that stack overflow would guarantee a stable business but now that “AI” has come into play, we can’t even keep up with demand. We’ll probably raise prices by 25% next quarter. By the time that AI can actually produce decent results, I can probably retire twice over.
Imagine making 500k TC but not contributing to open source
When I started doing open source software, that meant posting tarballs to Usenet and mailing list, occasionally mailing someone a hard floppy on request. I don’t have a github profile sparkling with emojies, but I think I’m doing all right.
These tools are game changers imo.
Personally I don’t use them to write code but to query how to do things.
It’s a massive productivity booster for me.
What a weirdly unjustified, baseless attack on someone contributing a useful conversation. And when presented with evidence that you’re not just being a huge jerk, that you’re entirely wrong, you get defensive and continue to denegrate OP?
Shame on you. If you have had half the illustrious career you claim to have, you should have worked in enough places and with enough people to know when to eat crow.
Infighting and personal attacks like this from positions of false authority like yours are exactly why people have such low opinions of programmers as members of society.
You should try copilot if you haven’t yet.
Copilot is great. I stopped paying for it after using ChatGPT so much (one subscription is expensive enough, as-is!) but I do miss it. Maybe I’ll buy it again…
Copilot regurgitates code verbatim and strips the licensing (see that one video of it spitting out Quake inverse sqrt). Don’t use it if you care about legality.
Quake inverse sqrt is one of the most famous algos in the world. Although I agree, if politicians actually stood for public interest they would force any AI derivative work to be SSPL or AGPL
Yes, its very famous. It’s also GPLed and Copilot had no right to use it in that way, and strip the license.
The largest button on the page is “stop” (???)
It’s there to be sure we find that button when Bard gets aspirations to take over the world or initiate thermonuclear warfare I suppose.
