[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / r / s / t / u / v / vg / vm / vmg / vr / vrpg / vst / w / wg] [i / ic] [r9k / s4s / vip] [cm / hm / lgbt / y] [3 / aco / adv / an / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / pw / qst / sci / soc / sp / tg / toy / trv / tv / vp / vt / wsg / wsr / x / xs] [Settings] [Search] [Mobile] [Home]
Board
Settings Mobile Home
/g/ - Technology


Thread archived.
You cannot reply anymore.


[Advertise on 4chan]


File: dfg.mp4 (291 KB, 576x1024)
291 KB
291 KB MP4
*mic drop
>>
>>107485019
What’s your point? I can find this kind of shit on GitHub and use that. Why would I spend money on an AI to do this (which will just be lifting from the GitHub code anyway)
>>
>>107485019
ChatGPT wins again
>>
>>107485101
Because one is whitewashed and the other is a licensed piece of code.
>>
>>107485275
So? I am white and follow the rules, if I was inconvienienced by the license, I'd just manually copy it but pretend that I wrote it myself.
>>
>>107485019
No wonder Claude can't beat Pokemon.
>>
How about asking it to do something that isn't easily found copy&pasted?
>>
>>107485462
but you didn't type "sage" in Comment field?
>>
>>107485019
Now ask Gemini to calculate how many standard drinks are in 2 19.5oz voodoo rangers + two 12oz voodoo rangers (all juice force flavor).
>>
File: file.png (194 KB, 1053x1346)
194 KB
194 KB PNG
>>107485733
>>
File: 1746528706252806.jpg (44 KB, 750x740)
44 KB
44 KB JPG
Wow the Deepseek one is that stupid? Didn't it blew everybody's mind back when it came out or something?
>>
File: ai-lmao-embedded.png (101 KB, 499x819)
101 KB
101 KB PNG
>>107485019
*picks up the mic*
*hits you over the head with it*
>>
File: images (1).jpg (10 KB, 233x216)
10 KB
10 KB JPG
>>107485019
Impressive.
Very nice.
Let's see Grok's attempt.
>>
post code
>>
>>107486789
is the way it talks down to you when you point out its mistakes some sort of mass demoralization campaign?
>>
>no copilot
test is void
>>
>>107485019
Claude wins again, doing it in 6 dimensional space.
We can't stop winning Claudesisters
>>
>>107485101
The ultimate black pill is that that statement is true for about 99% of code created today; just rehashes of the same problem with different API endpoints, label etc. The sort of stuff AI excels at.
>>
>>107485019
Claude's is truly an expression of something and therefor the best.
>>
>>107485019
sam is earning his gpus
>>
>>107486769
deepseek blew everyone's minds because it offered a comparable level of performance to frontier models at a fraction of the price
i don't think anyone claimed that it was actually better, but economically it was a miracle.
>>
>>107488312
>i don't think anyone claimed that it was actually better
nigger do you seriously expect nobody to remember the months-long spamwave?
>>
>>107485275
That's not even true and is just a lie that is being pushed, modern AI just does a web search and copy pastes the result. The whole circumventing copyright thing assumed it was the model generating the result, now it's literally has the exact code it's stealing in the context window and repeats back in the output.
>>
>>107488902
That anon is right, the reason there was a spam wave is because at one point in time its results were comparable to chatgpt, for a fraction of the cost. It made Altman seethe because it exposed the inefficiency of their system. It was never going to be able to keep up, I'm not sure why people still insist on using it for comparisons, it hasn't been relevant for a while now.
>>
>>107489109
Search AGI achieved on X and the spamwave continues
>>
>>107489114
Yeah, but not for deepseek
>>
>>107485019
So when it will do something worth half a trillion of dollars in money and God know how much dollars in hardware?
My 10yo niece can assemble Rubik's cube...
>>
>>107489543
Besides, are we not supposed to notice that most sciensists are getting paid by the two corporations that supposedly are getting the best results? Hard to take any AI research seriously when it's just Sam Altman and Sundar Pichai sloppily sucking each other off.
>>
>>107485019
None of those are names of models and ChatGPT is a website.
>>
>>107485019
Isn't Gemini ChatGPT, though?
>>
>>107487864
You zoomers sure are fragile
>>
>>107488902
One area it was worse in was coding
>>
File: file.png (101 KB, 3513x1146)
101 KB
101 KB PNG
I tried in Copilot, but I don't see anything
https://copilot.microsoft.com/shares/J4Y3oZvtcmh7Z7dxadAGD
>>
>>107485019
i really like chatgpts feature of memory between discussion threads. but gemini is such a step up i use it for hard stuff instead. if it got memory between threads, it would be over
>>
>>107485019
I don't know. Claude's interpretation arguably isn't *that* crazy.
>>
>>107489505
Yea for DeepSeek
>>
>>107489543
Post her feet in cute socks
>>
>>107485019
Schizo Claude = sovl
>>
File: Untitled.png (26 KB, 410x202)
26 KB
26 KB PNG
>>107485019
we just got too more weeks with this post
>>
>>107486253
The patched it in after it failed to calculate for me twice on Sunday.
>>
>>107491531
of course, buddy
>>
>>107491588
The total of the two 19.2 oz cans and two 12 oz cans of Voodoo Ranger Juice Force (9.5% ABV) is approximately 7.7 standard drinks in the U.S..
Breakdown of Standard Drinks
A U.S. standard drink contains about 0.6 fluid ounces of pure alcohol.
Two 19.2 oz cans:
Each can is approximately 3.2 standard drinks (19.2 oz * 0.095 ABV / 0.6 oz pure alcohol per drink).
Total for two cans: 6.4 standard drinks.
Two 12 oz cans:
Each can is approximately 1.1 standard drinks (12 oz * 0.095 ABV / 0.6 oz pure alcohol per drink).
Total for two cans: 2.2 standard drinks.
Overall Total:
6.4 standard drinks + 2.2 standard drinks = 8.6 standard drinks.
Correction in calculation:
19.2 * 0.095 / 0.6 = 3.04 standard drinks per can
12 * 0.095 / 0.6 = 1.9 standard drinks per can
Total: (2 * 3.04) + (2 * 1.9) = 6.08 + 3.8 = 9.88 standard drinks.
Let me recalculate based on the correct formula.
Corrected Breakdown
A U.S. standard drink contains approximately 14 grams or 0.6 fluid ounces of pure alcohol.
Two 19.2 oz cans:
Each can: (19.2 fl oz * 0.095 ABV) / 0.6 fl oz per drink = 3.04 standard drinks.
Total for two cans: 2 * 3.04 = 6.08 standard drinks.
Two 12 oz cans:
Each can: (12 fl oz * 0.095 ABV) / 0.6 fl oz per drink = 1.9 standard drinks.
Total for two cans: 2 * 1.9 = 3.8 standard drinks.
Overall Total:
6.08 standard drinks + 3.8 standard drinks = 9.88 standard drinks.
The total amount of alcohol across all four cans is nearly ten standard drinks.
Would you like to know the health guidelines related to this amount of alcohol consumption?
>>
>>107491642
Cont.
>How did you get 7.7
The previous calculation of 7.7 standard drinks was amathematical error. The correct total is9.88 standard drinks.

The mistake was likely due to a miscalculation of individual can totals (e.g., 2.2 standard drinks for the 12oz cans instead of the correct 3.8 total). The formula for a U.S. standard drink (0.6 fluid ounces of pure alcohol) was applied incorrectly in the final sum.

The current total of9.88 standard drinksis accurate based on the math:

Two 19.2 oz cans: 2 * ((19.2 oz * 0.095 ABV) / 0.6) =6.08 standard drinks.

Two 12 oz cans: 2 * ((12 oz * 0.095 ABV) / 0.6) =3.8 standard drinks.

Total:9.88 standard drinks.

Would you like a further breakdown of how the standard drink formula works?
>>
>>107491642
share link or it didnt happen
>>
500 trillion dollars and the entire world power grid to render a cube. based. so fucking based
>>
>>107491778
I'm just telling you what the chatbot told me. Continue coping I guess.
>>
>>107491836
>it works shit for me
>it works great for you
>go cope

sure bru
>>
here's another one
https://clocks.brianmoore.com



[Advertise on 4chan]

Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.