I’m one of the moderate fanboys and I love gpt5 and not having to switch models anymore, compared to before. So far, it’s pretty good about when to think longer and when to give quick answers.
That being said, I don’t use it for anything other than STEM concepts and coding tasks. I have no idea what the complainers use it for.
I did hear that people thought it had less “personality”. Funny, I did notice it got more concise in its answers. This was an improvement for me, but I’m using it as a tool, not a friend or therapist or something. To each their own.
A bit complaint I saw was that it was really bad at choosing when to think long and when to give short answers leading to lots of incorrect and underbaked replies.
Yeah, using the corporate version of chatgpt (Microsoft Copilot), it was a huge leap, Gpt 4 was dumb as hell, Gpt 5 is average in intelligence. I hate LLMs, but it makes my unit tests and help me debug the java magic at my job.
If you’re having success with your use cases, then good. Just be sure to verify the results, and that’s key because many people using LLMs aren’t looking hard at what they get but just copying it as right. When LLMs fail, they fail gloriously, because they don’t understand what they’re outputting since they aren’t AGI, even though they’re sold as such.
Yeah, I know. I just use it as “from this, I did this, so make the same process for this thing”, they statistically only try to guess the next token, so they are only good at these “from this work, do the same thing here”. The buggy code that I commit is artisanal, the tests are just copying from other tests.
I don’t know if any of them actually is, but it is claimed that GPT5 was tuned for the Indian tech sector, and the model fans replying to you sound like they belong to the target audience 😊
Wasn’t it a moderate success? While I dislike (even hate) LLM in general, many people I know loved new GPT5 compared to GPT4.
I’m one of the moderate fanboys and I love gpt5 and not having to switch models anymore, compared to before. So far, it’s pretty good about when to think longer and when to give quick answers.
That being said, I don’t use it for anything other than STEM concepts and coding tasks. I have no idea what the complainers use it for.
I did hear that people thought it had less “personality”. Funny, I did notice it got more concise in its answers. This was an improvement for me, but I’m using it as a tool, not a friend or therapist or something. To each their own.
A bit complaint I saw was that it was really bad at choosing when to think long and when to give short answers leading to lots of incorrect and underbaked replies.
Yeah, using the corporate version of chatgpt (Microsoft Copilot), it was a huge leap, Gpt 4 was dumb as hell, Gpt 5 is average in intelligence. I hate LLMs, but it makes my unit tests and help me debug the java magic at my job.
If you’re having success with your use cases, then good. Just be sure to verify the results, and that’s key because many people using LLMs aren’t looking hard at what they get but just copying it as right. When LLMs fail, they fail gloriously, because they don’t understand what they’re outputting since they aren’t AGI, even though they’re sold as such.
Yeah, I know. I just use it as “from this, I did this, so make the same process for this thing”, they statistically only try to guess the next token, so they are only good at these “from this work, do the same thing here”. The buggy code that I commit is artisanal, the tests are just copying from other tests.
Funny replies you got.
I don’t know if any of them actually is, but it is claimed that GPT5 was tuned for the Indian tech sector, and the model fans replying to you sound like they belong to the target audience 😊