Re: [問卦] chatgpt: 9.11-9.9 = 0.21?
AI先用語言編碼再進神經網路最後歸納演算
請用英文問且 關鍵字 要正確
calculate math 9.11-9.9 is?
ChatGPT 說:
The result of
9.11
9.9
9.11.9 is:
9.11
9.9
=
0.79
9.11.9=-.79
//另一段
I mean 9.11 - 9.9 = -0.79 but now 9.11 - 9.9 = 0.21
maybe it's not decimal maybe some situation can you list?
ChatGPT 說:
Ah, I get it now! You're asking for scenarios where the result of
9.11
9.9
9.11.9 could change from
0.79
.79 to
0.21
0.21, which might not involve decimal arithmetic. Here's a list of
possibilities where such a situation could occur:
1. Modulo Arithmetic
In modular arithmetic, results "wrap around" after reaching a certain value.
For example:
If we are working in modulo
1
1,
9.11
9.11 becomes
0.11
0.11 and
9.9
9.9 becomes
0.9
0.9.
Subtraction
0.11
0.9
0.11.9 in modulo
1
1 gives
0.21
0.21 (wrapping back around).
2. Custom Number Systems or Scales
The subtraction is performed in a non-decimal number system, such as:
Base-12 (duodecimal): Numbers in different bases can yield results that don'talign with decimal subtraction.
Arbitrary scale adjustment: For example,
9.11
9.11 and
9.9
9.9 are values scaled by a factor or offset, changing the subtraction outcome.3. Signed vs. Unsigned Interpretation
If the numbers are stored as signed vs. unsigned integers in computer systems:
9.11
9.9
9.11.9 could behave differently depending on how the system interprets
values.
Overflow or underflow in unsigned subtraction could result in a different
outcome.
4. Error Correction or Adjustment Factor
The calculation might include a hidden correction factor or adjustment:
Some systems might add a constant adjustment to ensure positive results.
For example, a constant
+
1
+1 correction:
(
9.11
9.9
)
+
1
=
0.21
(9.11.9)+1=0.21
5. Quantum or Probabilistic Systems
In quantum computing or probabilistic algorithms:
Subtraction results might not be deterministic, allowing
9.11
9.9
9.11.9 to
0.21
0.21 in
6. Time-Based Context
In specific contexts like timestamps:
9.11
9.11 and ( 9.9
9.9
9.9 might represent
7. Measurement Errors or Bias
In physical systems, results could change due to:
Mea
Bi
//
9.11 - 9.9 = -0.79 but now 9.11 - 9.9 = 0.21
maybe it's not decimal maybe some situation can you list?
ChatGPT 說:
Great catch! If
9.11
9.9
=
0.21
9.11.9=0.21, then the numbers might not be in decimal form. Let's explore
potential scenarios where this could make sense:
1. Base Systems (Non-Decimal)
Base 10 (Decimal):
9.11
9.9
=
0.79
9.11.9=.79, as calculated initially.
Base 12 (Duodecimal):
9.11
9.11 and
9.9
9.9 are interpreted in base 12.
9.11
12
=
9
+
1
12
+
1
144
9.11
12
=9+
12
1
+
144
1
9.9
12
=
9
+
9
12
9.9
12
=9+
12
9
Subtraction could yield
0.21
0.21 when converted to base 10.
2. Time Format (Hours and Minutes)
Hours and Minutes:
9.11
9.11 could mean 9 hours and 11 minutes.
9.9
9.9 could mean 9 hours and 90 minutes (or 10 hours and 30 minutes).
Subtracting
9
:
11
10
:
30
9:110:30 might give you
0
:
21
0:21 (21 minutes).
3. Measurement Systems
If
9.11
9.11 and
9.9
9.9 are part of a measurement system with specific units or rounding
conventions, the difference might result in
0.21
0.21.
4. Financial Rounding or Precision
In accounting or financial settings, numbers might be rounded or truncated
based on significant figures, giving a result of
0.21
0.21.
//
是我們想得太簡單 不見得AI有錯!!!
※ 引述《bengowa (鞭狗蛙 舒服)》之銘言:
: 乳題啦
: 我剛剛看到有人PO文說
: 如果你去問chatgpt一個簡單的減法問題
: 9.11-9.9=?
: 他會跟你說0.21
: 我本來想說 幹怎麼可能
: 結果測試後真的是這樣
: https://imgur.com/6cQOyFC.jpg
: 笑死==
--
看不懂 樓下翻成白話文
「AI沒有錯!(笑)」
本版不缺 稻草人論證 99.99% 都如此 不見得AI有錯!!! -> 「AI沒有錯!(笑)」 某問:支持妓女有權做生意嗎? 我回:支持! -> 你一定去嫖過妓
建構式數學加上文字邏輯...好像台灣現
在在教小朋友的那套啊
DeepSeek完全沒問題
DeepSeek一開始就以中文編碼中文問剛好
這裡有簡易版的gpt, bert chatbot model 稍微懂一點也就了解AI問題出在那了
https://tinkerd.net/blog/machine-learning/bert-embeddings/※ 編輯: feelthat (114.32.93.159 臺灣), 02/06/2025 19:06:41
77
首Po乳題啦 我剛剛看到有人PO文說 如果你去問chatgpt一個簡單的減法問題 9.11-9.9=? 他會跟你說0.21![[問卦] chatgpt: 9.11-9.9 = 0.21? [問卦] chatgpt: 9.11-9.9 = 0.21?](https://i.imgur.com/6cQOyFCb.jpg)
→ nekoares: 「AI沒有錯!(笑)」 111.248.102.98 02/06 16:32 本版不缺 稻草人論證 99.99% 都如此 不見得AI有錯!!! -> 「AI沒有錯!(笑)」 某問:支持妓女有權做生意嗎? 我回:支持! -> 你一定去嫖過妓3
各位肥宅安ㄍ 小弟是時薪138元的人森勝利組飲料店秘書長顧問仔。 祕書長工作關係有用ChatGPT協助泡飲料啦。 你這個就是用免費的啊,免費的比較笨 祕書長用到的是尊爵不凡650元的訂閱版![Re: [問卦] chatgpt: 9.11-9.9 = 0.21? Re: [問卦] chatgpt: 9.11-9.9 = 0.21?](https://i.imgur.com/hWxWNvKb.jpeg)
9
我是不是在平行時空啊? 我問了兩次都是對的啊 也沒付費啊,就那個適用日常交談的版本![Re: [問卦] chatgpt: 9.11-9.9 = 0.21? Re: [問卦] chatgpt: 9.11-9.9 = 0.21?](https://i.imgur.com/ZNhZX7vb.jpeg)
→ cs09312: 所以結論是chatgpt抄DS嗎 39.9.67.159 02/06 18:55 ※ 編輯: feelthat (114.32.93.159 臺灣), 02/06/2025 19:06:11 兩個回應指定性的問題所給的答案 95% 一致 那為什麼DS 感覺比Chatgpt 好 你設計一些金融問題 你會發現 Chatgpt 活在2023年
爆
[分享] 9/9(五)-9/11(日)【鬼滅之刃】9/9(五)-9/11(日)【鬼滅之刃】 天色漸黑,兄弟們換上鬼滅之刃聯名球衣, 將在臺中洲際棒球場進行連續三日的奮戰拚搏! 夥伴們換上你的鬼滅聯名球衣,一起到洲際棒球場大顯身手,奮力一戰! 2022中信兄弟【鬼滅之刃】主題日![[分享] 9/9(五)-9/11(日)【鬼滅之刃】 [分享] 9/9(五)-9/11(日)【鬼滅之刃】](https://i.imgur.com/1V5ygFnb.jpg)
56
Re: [爆卦] OpenAI 新模型o1輕鬆考上台大資工/台大剛推出出來的時候我拿了幾題邏輯題出來考他 正確率很高我很驚喜覺得太神啦 剛剛看到下面推文 說他答不出來9.9跟9.11誰比較大 我想說不可能這麼簡單的答不出來吧![Re: [爆卦] OpenAI 新模型o1輕鬆考上台大資工/台大 Re: [爆卦] OpenAI 新模型o1輕鬆考上台大資工/台大](https://img.youtube.com/vi/4EayaPNo6pk/mqdefault.jpg)
46
[分享] 9/9(五)、9/10(六)內野上層門票開放預售兄弟官方FB: 9/9(五)-9/11(日)【鬼滅之刃】X9/9(五)、9/10(六)內野上層門票開放預售 9/9-9/11中秋連假~ 首次現象動漫「鬼滅之刃」聯名主題日熱血登場! 天色漸黑,兄弟們換上鬼滅之刃聯名球衣,![[分享] 9/9(五)、9/10(六)內野上層門票開放預售 [分享] 9/9(五)、9/10(六)內野上層門票開放預售](https://i.imgur.com/Y3DMFxob.jpg)
23
[情報] yahoo拍賣22週年慶活動yahoo拍賣22週年慶活動 主要還是免運和拿超贈點 活動說明: ▶9/6-9/22 天天開寶箱 超值好禮天天賺19
[閒聊] 9/9及9/11觸身球爭議3壘側錄畫面9/9(三) 阜林觸身球申請電視輔助判決─挑戰失敗 9/11(五) 傑憲觸身球申請電視輔助判決─挑戰失敗 因為我都坐三壘側17
[情報] 【鬼滅之刃】 9/11(日)GUEST-孫沁岳9/9(五)-9/11(日)【鬼滅之刃】 9/11(日)GUEST-孫沁岳 Yorke 最會說動漫的藝人孫沁岳來到中信兄弟鬼滅之刃主題日 身兼演員、歌手的孫沁岳現在多了YOUTUBER身分 以動漫為頻道主題,推出【漫遊快譯通】系列影片!![[情報] 【鬼滅之刃】 9/11(日)GUEST-孫沁岳 [情報] 【鬼滅之刃】 9/11(日)GUEST-孫沁岳](https://i.imgur.com/pffB21Qb.jpg)
11
[爆卦] 塔利班沒有要在911就職阿昨天不是說塔利班要選911就職典禮嗎?? 結果香港媒體早就在9/9號說根本就沒這個事情 俄羅斯媒體也說沒有 然後英國媒體一直說有 結果台灣這邊傳的很像真的 可能的理由現在都在亂傳![[爆卦] 塔利班沒有要在911就職阿 [爆卦] 塔利班沒有要在911就職阿](https://i.imgur.com/qmnNeLIb.jpg)
2X
[情報] 老高講 deepseek 好生動說得好誇張 老高果然是說書人 9.9 > 9.11 現在o1是可以正確回答 --![[情報] 老高講 deepseek 好生動 [情報] 老高講 deepseek 好生動](https://img.youtube.com/vi/uKBI1Ea8VO0/mqdefault.jpg)
[問卦] 慟!llama3.2 90b是廢了嗎?它回9.11>9.9!慟! 本著激動的心, 顫抖的手, 好不容易下載完llama 3.2 90b fp16, 載入這個號稱能打敗Chat-GPT 4o的模型後,
[閒聊] 法環 炸彈超人笑死 沒想到炸彈超人 我的超人 竟然法環也有911![[閒聊] 法環 炸彈超人 [閒聊] 法環 炸彈超人](https://img.youtube.com/vi/p0aCSxqf_64/mqdefault.jpg)