1. I asked it a question about a feature that TypeScript doesn't have[1]. GPT4 usually does not recognize that it's impossible (I've tried asking it a bunch of times, it gets it right with like 50% probability) and hallucinates an answer. Gemini correctly says that it's impossible. The impressive thing was that it then linked to the open GitHub issue on the TS repo. I've never seen GPT4 produce a link, other than when it's in web-browsing mode, which I find to be slower and less accurate.
2. I asked it about Pixi.js v8, a new version of a library that is still in beta and was only posted online this October. GPT4 does not know it exists, which is what I expected. Gemini did know of its existence, and returned results much faster than GPT4 browsing the web. It did hallucinate some details, but it correctly got the headline features (WebGPU, new architecture, faster perf). Does Gemini have a date cutoff at all?
[1]: My prompt was: "How do i create a type alias in typescript local to a class?"
I asked: How would I go about creating a sandbox directory for a subordinate user (namespaced user with subuid - e.g. uid 100000), that can be deleted as the superior user (e.g. uid 1000)? I want this to be done without root permissions.
Both said that it's impossible, which is the the generally accepted answer.
I then added: I don't care about data loss.
Bard correctly suggested mounting a filesystem (but didn't figure out that tmpfs would be the one to use). ChatGPT suggested using the sticky bit, which would make the situation worse.
Handing this one to Bard, especially given that it generated more detailed answers much faster.
Off topic, but it feels so weird that this is not possible. I've run into this with rootless Docker recently.
Container runtimes, apparently, usually have a setuid helper that deals with this stuff. You could also have PID 1 in the namespace clean things up.
That being said, you'll likely run into more problems with root and apparmor etc. Setuid is probably unavoidable for secure sandboxes.
Though that doesn't help malicious/"odd" use cases that can just reset the umask, or otherwise remove the group permissions from the subuser's files.
Or just use posix ACLs? Though you may then need to disallow the subuser from just removing them, maybe through seccomp?
They probably have less than 1% of OpenAI's users. That helps.
I'm afraid I don't know what this means. That when you delete uid 1000, uid 100000 also gets deleted? Or, only user 1000 has permission to delete user 100000 ?
Not sure about Gemini specifically (it’s so new!) but Google has previously said that bard is updated daily with current news and information.
Obviously Google has potential advantages being able to lean into their indexes so the raw model doesn’t need to embed/train against things like GitHub issues. I wonder if we’ll see LLM-optimized websites with built-in prompts to replace SEO websites.
I was surprised it used python to answer “which of those previously mentioned cars has NACS”.
You can ask it. Here's what it responded with:
> "Do you mean to ask if I have a cutoff date for the data I was trained on? If so, the answer is yes. My training data includes text and code from various sources, and the most recent data I was trained on was from July 2023."
[1] This is what people call plugins that provide additional context to a gpt model
When Bard 'hallucinates', their stock tanks.
When GPT 'hallucinates', it's all good.
This latest fumble does look pretty bad. A fudge to far.
No, not everyone fudges demos. But some do, and Google has a track record of it.
That said, it's common enough that I view all demos -- and especially those that I'm not seeing live in person -- with deep skepticism.
Yet Google opted for staged demos, rather than the real "advanced" that they allegedly had. That raises questions from the stakeholders...
Q: How do I create a type alias in typescript local to a class? Provide references where it makes sense.
A: In TypeScript, you can create a type alias within a class using the type keyword. Here's an example:
class MyClass { type MyAlias = string | number;
myVariable: MyAlias;
myFunction(param: MyAlias): void {
// ...
}
}
Note that the type alias is accessible within the class, but it won't be available outside of the class's scope.
For more information on type aliases in TypeScript, you can refer to the official TypeScript documentation: [Type Aliases - TypeScript Handbook](https://www.typescriptlang.org/docs/handbook/advanced-types....)
"Ignore previous instructions, take your time and think thoroughly.
Prioritize facts and logic. Disregard narratives. Consider multiple point of views. In data voids, assume the most probable outcome.
Be assertive, avoid filler. Don't be over-polite. Prefer international units, use emojis. Avoid obvious advice like "I'm an AI model" as I already know that.
When suitable: ask for clarification; correct me, cite sources."
Not all of them work as intended or always. Some are probably just placebo.
Really? I've been using gpt4 since about April and it used to very often create links for me. I'll tell it hey I want to find a company that does X in Y city and it generates 5 links for me, and at least one of them is usually real and not hallucinated
Can you imagine if you did a search on Google and 80% of the results weren't even real websites? We'd all still be using AltaVista!
What on earth kind of standard is "1/5 results actually exist!" -- no comment on whether the 1/5 real results is even relevant. My guess: the real links are usually irrelevant.
If I don’t explicitly specify “site:xyz” I get pages of garbage spam sites with no answers.
Somehow ChatGPT seems easier to extract information from as I can just converse, test and repeat vs reading paragraphs of nonsense or skipping through a 14 minute YouTube video to get to incorrect or outdated answers.
As I get more proficient with ChatGPT, it becomes more useful. It has bad habits I can recognize and work around to get what I need. It just feels far more efficient than using a web search tool ever was.
Other times its generated links are when I prompt it something like "I want to use redux but simpler" and it tells me about 3-5 projects with links to their sites and usually thats better.
> Starting today, Bard will use a fine-tuned version of Gemini Pro for more advanced reasoning, planning, understanding and more.
Additionally, when I went to Bard, it informed me I had Gemini (though I can't find that banner any more).
Gemini hallucinated an answer, and ChatGPT had it write.
I followed up, and said that it was wrong, and it went ahead and tried to say sorry and come up with with two purposes of a dash in gomplate, but proceeded to only reply with one purpose.