על מה אתה חושב?
- Dror Gill
- 26 בינו׳
- זמן קריאה 4 דקות

זה מרתק לראות איך מודלים של חשיבה "חושבים".
מודלי חשיבה (Reasoning Models) הם סוג חדש של מודלי שפה גדולים (Large Language Models), ש-"חושבים" לפני שהם עונים. הם משתמשים בטכניקות של שרשרת חשיבה (Chain-of-Thought) כדי לפרק משימה לסדרה של משימות קטנות יותר, ויש להם "מחברת״ פנימית שבה הם כותבים את ה-"מחשבות" שלהם כשהם עובדים על משימה. הצצה ל-"מחברת" הזו מלמדת אותנו איך המודלים האלה חושבים.
יש היום 3 מודלי חשיבה שזמינים לכל המשתמשים: OpenAI o1, DeepSeek R1 (המכונה DeepThink), ו-Google Gemini Flash 2.0 Thinking Experimental, שזמין ב-Google AI Studio. מודל OpenAI o1 מראה רק גרסה מסוננת ומסוכמת של ה-"מחשבות" שלו, בעוד ש-Gemini ו-DeepSeek חושפים את המחשבות ״האמיתיות״ שלהם.
נתתי לכל שלושת המודלים את אותה המשימה: "תחלץ כמה שיותר מילים מהמילה 'Connectivity'". המודל DeepSeek R1 "חשב" במשך שתי דקות כמעט, והגיע ליותר מ-100 מילים. הוא התחיל במחשבה הבאה:
"Okay, so I need to extract as many words as possible from the word "Connectivity". Let me start by writing down the letters in "Connectivity" and see how they can be rearranged.
First, let's list out all the letters. C, O, N, N, E, C, T, I, V, I, T, Y. Wait, let me check again. The word is C-O-N-N-E-C-T-I-V-I-T-Y. So letters are: C (1), O (1), N (2), E (1), C (2), T (2), I (2), V (1), Y (1). So two Cs, two Ns, two Ts, two Is, and one each of O, E, V, Y.
I need to find all possible words, including shorter ones. Let's start with the longest possible words first. Maybe "Connect" is there. C-O-N-N-E-C-T. Yes, that's part of "Connectivity". So "Connect" is a 7-letter word. Then maybe "Connection", but that would require an extra O and N, but "Connectivity" only has two Ns. Wait, "Connection" is C-O-N-N-E-C-T-I-O-N, but in "Connectivity", there's only one O, so "Connection" would need two Os. So that's not possible. So "Connect" is valid."
ואז הוא המשיך לחקור את המשימה, והעלה עוד מחשבות שנעשו די מוזרות:
"Now shorter words. Let's think of 6-letter words. Maybe "Connie" – C-O-N-N-I-E. But we have two Ns, one I. Wait, "Connie" would need two Ns, which we have, and one I. But in the original word, there are two Is. So that's okay. Wait, "Connie" is C-O-N-N-I-E. But "Connectivity" has E, so yes. So "Connie" is possible. Is that a valid word? I think so, as a name, but maybe not a common noun. Let me check if that's acceptable. The user didn't specify if proper nouns are allowed. Hmm, maybe stick to common words."
"חכה". "הממ". "אני חושב שכן". "תן לי לבדוק".
אחר כךבדקתי את Gemini 2.0 Flash Thinking. הוא "חשב" במשך 7 שניות בלבד, ומצא רק 63 מילים. כשביקשתי ממנו להסיר כפילויות, נשארו רק 55 מילים. זה היה תהליך החשיבה הראשוני שלו במשימה הזו:
Here's a thinking process to generate words from "Connectivity":
Understand the Goal: The request is to extract as many words as possible from "Connectivity". This implies looking for shorter words, longer words, and variations within the letters provided. It's not about anagrams using all the letters, but rather finding substrings within the word that are valid English words.
Break Down the Word: Mentally break down "Connectivity" into smaller chunks and consider prefixes, suffixes, and root words if any are apparent. Visually scan the word letter by letter, looking for common letter combinations that start words.
C-O-N-N-E-C-T-I-V-I-T-Y
Systematic Approach (Left to Right): Start from the beginning of the word and move letter by letter, trying to form words.
C: "Con", "Connect"
O: "On", "One"
N: "No", "Not"
N: (again, from this 'N') "Net"
E: "Eat", "Even", "Event"
C: "Cat", "Cot", "Cite"
T: "Tea", "Ten", "Tie", "Tiny", "Tent"
I: "In", "It", "Ice"
V: "Vet", "Vine", "Vice", "Very"
I: "Is", "If"
T: "To", "Toe", "Tip"
Y: "Yes", "Yet", "You" (though 'you' uses an 'o' which isn't available consecutively - reconsider 'you' - no good). "Yet" is valid.
ואז הוא ממשיך בגישה של מימין לשמאל, ומנסה למצוא מילים ארוכות יותר:
Look for Longer Words: Once you have some shorter words, try to combine or extend them within the letters of "Connectivity" to find longer words.
"Connect" is already there. "Connection"? No extra 'o' needed, but we don't have another 'o' after 'n'. "Connective"? Yes! "Connectivity" (the original word itself counts!)
"לפרק מנטלית". "לסרוק ויזואלית". "לשקול מחדש". "לא טוב".
ולבסוף, המודל OpenAI o1 "חשב" במשך 2 דקות ו-43 שניות, והגיע רק ל-54 מילים. כך הוא סיכם את תהליך ה-"מחשבה" שלו (ושוב, שימו לב שבמקרה של o1 אלו לא "מחשבות" אמיתיות):
Breaking down letters
I’m analyzing the letters in "Connectivity" to extract smaller, valid English words, ensuring each letter's frequency is respected. This process helps in identifying potential subwords efficiently.
Reassessing letter count
I’m confirming "Connectivity" has 12 letters with frequency: C: 2, O: 1, N: 2, E: 1, T: 2, I: 2, V: 1, Y: 1. This ensures accuracy for identifying subwords.
Identifying subwords
I'm grouping words based on their letter frequency from "Connectivity," ensuring each letter's occurrence is respected. This method helps systematically uncover as many valid English subwords as possible.
Evaluating options
I’m thinking through words like "inventive," "invite," "incite," "civic," and "vicinity," ensuring the frequency of each letter aligns with "Connectivity." Progress is evident as each word is carefully evaluated.
"אני מנתח". "אני מאשר". "אני חושב". "התקדמות נראית לעין".
זה מרתק להתבונןן לתוך המחשבות של המכונה.
Yorumlar