11–20 of 20 posts
I'm still not sure what model to use for what task. Which oddly sounds like a great task for chatgpt to solve
But hold on. 5 in LIVE5TREAM for gpt 5 or 5 models or 5 modals? Luckily we already have 4.5 so can’t be it, right?
It may be GPT-4.55 as well. I find it really funny to explain someone non technical versioning of LLM models of different companies.
But hold on. 5 in LIVE5TREAM for gpt 5 or 5 models or 5 modals? Luckily we already have 4.5 so can’t be it, right?
We have 4o and o4 (and hilariously, a 4o-mini and an o4-mini), so maybe we should anticipate whatever creates the most naming chaos possible.
Hopefully a major focus on tools, the models are "good enough" at coding, but tool usage lags behind substantially.
What models have you been using? None of the popular public ones are even close to “good enough” for me. They still surprise me and have value, but are not good enough.
But hold on. 5 in LIVE5TREAM for gpt 5 or 5 models or 5 modals? Luckily we already have 4.5 so can’t be it, right?
We have 4o and o4 (and hilariously, a 4o-mini and an o4-mini), so maybe we should anticipate whatever creates the most naming chaos possible.
I remember being soooo excited to see what new iPhone features there would be. A must watch live moment.
Now apple keynotes contains very few surprises, and if there are any they’re leaked ahead of time.
Hopefully a major focus on tools, the models are "good enough" at coding, but tool usage lags behind substantially.
I'm still not sure what model to use for what task. Which oddly sounds like a great task for chatgpt to solve
Really shows how much the quality of the HN community has changed.
I'm still not sure what model to use for what task. Which oddly sounds like a great task for chatgpt to solve
4o for straightforward stuff that takes one or two steps to complete. o3 for everything more complicated than that.
Ignore the rest of the models.