Most active commenters

    ←back to thread

    OpenAI o3 and o4-mini

    (openai.com)
    555 points maheshrijal | 11 comments | 16 Apr 25 17:01 UTC | HN request time: 0.209s | source | bottom
    Show context
    testfrequency ◴[16 Apr 25 17:11 UTC] No.43707831[source]▶
    As a consumer, it is so exhausting keeping up with what model I should or can be using for the task I want to accomplish.
    replies(9): >>43707851 #>>43707929 #>>43707933 #>>43707962 #>>43707978 #>>43708283 #>>43708958 #>>43709741 #>>43710449 #
    1. energy123 ◴[16 Apr 25 18:47 UTC] No.43708958[source]▶
    Gemini 2.5 Pro for every single task was the meta until this release. Will have to reassess now.
    replies(3): >>43708968 #>>43709096 #>>43712077 #
    2. hollerith ◴[16 Apr 25 18:48 UTC] No.43708968[source]▶
    Huh. I use Gemini 2.0 Flash for many things because it's several times faster than 2.5 Pro.
    replies(2): >>43709677 #>>43710695 #
    3. blueprint ◴[16 Apr 25 19:00 UTC] No.43709096[source]▶
    how do you deal with the fact that they use all of your data for training their own systems and review all conversations
    replies(2): >>43711739 #>>43713052 #
    4. mring33621 ◴[16 Apr 25 19:57 UTC] No.43709677[source]▶
    Agreed.

    I pretty much stopped shopping around once Gemini 2.0 Flash came out.

    For general, cloud-centric software development help, it does the job just fine.

    I'm honestly quite fond of this Gemini model. I feel silly saying that, but it's true.

    5. jug ◴[16 Apr 25 21:39 UTC] No.43710695[source]▶
    Yes, this one is addictive for its speed and I like how Google was clever and also offered it in a powerful reasoning edition. This helps offset deficiencies from being smaller while still being cheap. I also find it quite sufficient for my kind of coding. I only pull out 2.5 Pro on larger and complex code bases that I think might need deeper domain specific knowledge beyond the coding itself.
    6. sharkjacobs ◴[17 Apr 25 00:17 UTC] No.43711739[source]▶
    gemini-2.5-pro-preview-03-25 is the paid version which doesn't use your data

    https://ai.google.dev/gemini-api/terms#data-use-paid

    replies(1): >>43712209 #
    7. thom ◴[17 Apr 25 01:13 UTC] No.43712077[source]▶
    Mad tangent, but as an old timey MtG player it’s always jarring when someone uses “the meta” not to refer to the particular dynamics of their competitive ecosystem but to a single strategy within it. Impoverishes the concept, I feel, even in this case where I don’t actually think a single model is best at everything.
    replies(1): >>43712444 #
    8. hirvi74 ◴[17 Apr 25 01:33 UTC] No.43712209{3}[source]▶
    I do not feel like I can trust the empire that was built off selling personal data.

    Make no mistake, I doubt the other options are trustworthy too.

    9. hatefulmoron ◴[17 Apr 25 02:15 UTC] No.43712444[source]▶
    I'm a World of Warcraft & Dota 2 player, using "the meta" in that way is pretty common in gaming these days I think. The "meta" is still the 'metagame' in the competitive ecosystem sense, but it also refers to strategies that are considered flavor of the month (FOTM) or just generally safe bets.

    So there's "the meta", and there's "that strategy is meta", or "that strategy is the meta."

    replies(1): >>43714067 #
    10. CaptainFever ◴[17 Apr 25 04:13 UTC] No.43713052[source]▶
    Personally, I frankly do not care for most things. But for more sensitive things which might land me in trouble, local models are the way to go.
    11. thom ◴[17 Apr 25 07:37 UTC] No.43714067{3}[source]▶
    Yeah, I accept that "Nash equilibrium" isn't likely to catch on at this stage.