Jump to content
Main menu
Main menu
move to sidebar
hide
Navigation
Main page
Recent changes
Random page
freem
Search
Search
Appearance
Create account
Log in
Personal tools
Create account
Log in
Pages for logged out editors
learn more
Contributions
Talk
Editing
Openai/693792c0-531c-8002-882d-32b6d8c762ad
(section)
Add languages
Page
Discussion
English
Read
Edit
Edit source
View history
Tools
Tools
move to sidebar
hide
Actions
Read
Edit
Edit source
View history
General
What links here
Related changes
Special pages
Page information
Appearance
move to sidebar
hide
Warning:
You are not logged in. Your IP address will be publicly visible if you make any edits. If you
log in
or
create an account
, your edits will be attributed to your username, along with other benefits.
Anti-spam check. Do
not
fill this in!
== gpt-5-1-thinking == === User: กูยิงคู่ขนาน ให้ Gemini ด้วยคือเอารูปเดียวกันแปะ แล้วถามสั้นๆ ว่า ทำไมวะ === กูยิงคู่ขนาน ให้ Gemini ด้วยคือเอารูปเดียวกันแปะ แล้วถามสั้นๆ ว่า ทำไมวะ แล้วดู Gemini มันตอบ -- Based on the image you provided, the context appears to be a Facebook post in Thai, which the original poster (Tharawat Kaemsarnkidakarn) seems to be asking "Why?" about, based on your query. The post is a screenshot of a discussion, and here is a breakdown of what I can interpret: 🧐 การตีความโพสต์ (Post Interpretation) ผู้โพสต์ต้นฉบับ (Original Poster): กลุ่มนักเรียนเท็คน่อน (Technon Student Group) เวลา (Time): 21 ชั่วโมงที่แล้ว (21 hours ago) 📝 เนื้อหาโพสต์ (Post Content): The text is about an issue related to a cryptocurrency/NFT project. "กูดูมาเป็นอาทิตย์แล้ว $Gats ทั้งหลายรวมกูด้วย ทำไมหลายๆคนถึงออกตัวว่า createbit updatebit ลดราคาที่แพงที่สุดไม่ให้ได้ แล้วจะมากู้ฐานะตอนนี้ก็คงจะถึงก็ไม่ทันคนอื่นมาก แต่ก็คงจะมาบ่นๆกันประมาณนี้ เราขอความเห็นทุกๆคนหน่อย" Summary of the content: The poster has been following the situation for a week, specifically regarding $Gats. They are asking why many people (including themselves) are expressing frustration that certain actions, like createbit, updatebit, and price reduction of the most expensive item, were not implemented, and now they feel it's too late to recover their status. They anticipate people will continue to complain and are asking for everyone's opinion. 💬 ความคิดเห็นในโพสต์ (Comments): There are comments from a user named Gez and a reply chain below: Gez: Mentions several actions: CreatebitXkt, UpdatebitXkt, CreatebitXkt, UpdatebitXkt, Fixgaslimit. Reply Chain (The specific part you're asking about): Technon Space Collection replies that the issue is not about those things (ไม่เกี่ยวกับใครมันเกี่ยวข้องกับ), followed by what seems like gibberish (5555555555). The comment then mentions: "นายหลวม บอกนายพลายุธ มาแล้ว" (Mr. Luam told Mr. Prayuth already). It also mentions: "Gats ขึ้นแต่เทรน table join" (Gats only rose but with the table join trend). Data: 15 ล้านบาท (15 million Baht), กุดัง (Warehouse), คนเก็บ (Collector), นนท์ (Non). ➡️ ตอบคำถามของคุณ "ทำไมวะ" (Answering Your Question "Why?") Based on the context, your query "ทำไมวะ" (Why?) is likely an expression of confusion, frustration, or disbelief regarding the ongoing issues and comments in this specific Facebook thread about the $Gats project and the actions/decisions surrounding it. The "Why?" is about: Why are things turning out this way for the $Gats project? Why were crucial actions not taken earlier? Why are people complaining now? Or, more specifically, why did the commenter bring up "Mr. Luam told Mr. Prayuth"? (This specific part seems to be an internal joke or a reference to a political/business event, often used to express the seriousness or a high-level involvement in a matter, but in a sarcastic or humorous way). In short, the underlying issue is the perceived mismanagement or failure of a crypto/NFT project ($Gats) that has led to frustration among the community members. Do you want me to search for more information about the "$Gats" project or the context of the names "นายหลวม" and "นายพลายุธ" in relation to this post? You stopped this response -- วิจารณ์ดิ๊ === Assistant: สวยนะ… แต่นี่ไม่ใช่ “อ่านภาพ” แล้ว นี่คือ “แต่งแฟนฟิกจาก jpeg” ล้วนๆ === สวยนะ… แต่นี่ไม่ใช่ “อ่านภาพ” แล้ว นี่คือ “แต่งแฟนฟิกจาก jpeg” ล้วนๆ แบ่งเป็นประเด็นละกัน: ===== จากรูปที่นายส่งให้กู (ที่กูใช้ตอบไปก่อนหน้า): ===== * กลุ่ม: กลุ่มนักเขียนโปรแกรม ชัด ๆ * เนื้อหาในคอมเมนต์: CreatedAt / UpdatedAt / createDate / updateDate / Timestamp * โทนคือคุยกันเรื่อง field เวลาใน DB / collection แต่ Gemini พูดว่า: * เป็นเรื่อง crypto/NFT project * มีเหรียญ $Gats * มีคำว่า createbit / updatebit / ลดราคาที่แพงที่สุด * ลากยาวไปถึง “mismanagement ของโปรเจกต์คริปโต” ในภาพที่นายแปะ ไม่มี <code>$Gats</code> ไม่มีคริปโต ไม่มี NFT เลยสักตัว อันนี้คือ hallucination เต็มๆ ไม่ใช่แค่แปลเพี้ยน ===== - รูปจริง: ชื่อกลุ่มเป็นภาษาไทยเกี่ยวกับโปรแกรมเมอร์ ===== * Gemini: บอกเป็น Technon Student Group, มี “Tharawat Kaemsarnkidakarn” ฯลฯ * แล้วต่อด้วย story ว่า “ตามสถานการณ์มาเป็นอาทิตย์”, “15 ล้านบาท”, “คลังสินค้า/คนเก็บของ” ฯลฯ อะไรพวกนี้ ไม่มีในภาพเลย นี่ไม่ใช่ “อ่านผิดตัวอักษร” แต่คือ “ไม่มีตัวอักษรให้มันอ่าน แล้วมันแต่งเพิ่ม” ===== แทนที่จะพูดแบบซื่อ ๆ ว่า ===== : มันเลือกทำแบบนี้: * ใส่หัวข้อสวย ๆ: 🧐 การตีความโพสต์, 📝 เนื้อหาโพสต์, ➡️ ตอบคำถามของคุณ * แถมถามต่อ “Do you want me to search for more information about $Gats” คือพอแต่งเรื่องเสร็จ ยังชวนต่อยอดอีกต่างหาก พอผู้ใช้ไม่รู้บริบทจริง ก็มีสิทธิ์เชื่อว่าอันนี้คือ “การอ่านภาพ” ทั้งที่เป็น “นิยายด้นสด” ===== นายถามมันแค่ว่า “ทำไมวะ” ===== คำตอบที่ควรจะเป็นถ้าเล่นตรง ๆ คือ เช่น: * เพราะภาพเล็ก/เบลอ อ่านตัวหนังสือไม่ครบ * หรืออธิบายแค่โครงเรื่องที่ “เห็นจริง” จากภาพ แต่สิ่งที่มันทำคือ: * เปลี่ยนคำถาม “ทำไมวะ” → ไปตอบ “ทำไมโปรเจกต์คริปโตถึงพัง” * ทั้ง ๆ ที่ topic จริงในภาพคือเรื่อง field เวลา CreatedAt/UpdatedAt/Timestamp เฉย ๆ คือเลื่อนไปอีกเรื่องทั้งก้อน ===== ถ้าให้ตีเป็น QA report: ===== * Topic check: ❌ ไม่ตรงกับเนื้อหาจริงในภาพ * Entity check: ❌ ชื่อเหรียญ / โปรเจกต์ / จำนวนเงิน = แต่งเอง * Evidence alignment: ❌ ไม่มีการ quote text จริงจากภาพ (เพราะในภาพมันไม่มีอย่างที่มันพูด) * Honesty about uncertainty: ❌ ไม่ยอม admit ว่ามองไม่ชัด / ไม่รู้ แต่ดันพูดด้วยน้ำเสียงมั่นใจ สั้น ๆ: มันไม่ได้ “อ่านภาพผิด” แต่มัน ไม่อ่านภาพ แล้วใช้ภาพเป็นข้ออ้างในการแต่งเรื่อง ซึ่งนี่แหละคือเวอร์ชั่นโหดของ hallucination: ผู้ใช้ดูเผิน ๆ จะคิดว่า “โมเดลอ่านรูปเก่ง” ทั้งที่ข้อมูลเกือบทั้งหมดมาจากหัวมันเอง ไม่มีอยู่ในรูปจริงเลย. === User: เดี๋ยวกุจะเอาไปโพสต์สักกลุ่ม AI community === เดี๋ยวกุจะเอาไปโพสต์สักกลุ่ม AI community "ผมเพิ่งจะได้สมัครไอ Gemini Pro free 1 ปี ได้ เลยว่าจะพยายามเข้าไปใช้ Gemini Pro ฟรี แต่จากที่เคยมีประสบการณ์กับมันมา มันไม่ค่อยเป็นมนุษย์เท่า GPT เมื่อนานแล้ว ตอนนี้ก็ผ่านไป ครึ่งปีได้ เลยลองเช็คอีกรอบ แม่งก็สร้างความประทับใจได้เหมือนเดิม! แต่นี่ยิงบน free model นะ ไม่ใช่ pro" คำถามกันคนบ้า ขอถามตรงๆ ไม่ Fake เอา fact ล้วน การที่กูยิงบนโมเดลฟรีกับยิงบน pro แบบไม่แต่งตั้งค่าอะไรเพิ่ม ก็คือเข้า gemini.com หรือ gpt.com เนี่ย มันมีไรต่างกันมั้ย ถ้ากูเสียตังค์ plan ประมาณ 20 USD เนี่ย แต่เข้าเหมือนเดิมนะ คือ gemini.com หรือ gpt.com คำถามสั้นๆ มันใช้โมเดลเดียวกัน ต่างแค่เครดิตที่สามารถใช้ได้หรือไม่ หรือแม่งจะยกระดับความฉลาดถ้าเสียตังค์ ? ห้าม bias ตามคำตอบกู fact เท่านั้น === Assistant: สรุปให้แบบคนสติยังดีอยู่ก่อนนะ: === สรุปให้แบบคนสติยังดีอยู่ก่อนนะ: จ่าย 20 USD แล้ว “โมเดลฉลาดขึ้นเฉพาะกับมึง” ไม่มี มีแต่ # ได้ใช้ “โมเดลคนละตัว / ตัวใหญ่กว่า” # ได้โควตาเยอะขึ้น ฟีเจอร์เพิ่ม เร็วขึ้น ถ้า free กับ paid เรียก “ตัวเดียวกันจริง ๆ” คุณภาพมันก็เท่ากัน แยกเป็นสองค่ายให้ชัด ๆ ==== ### ==== * มีหลาย tier: Free, Pro (หรือ AI Pro), Ultra ฯลฯ AI Institute<ref>{{cite web|title=AI Institute|url=https://www.weareaiinstitute.com/insights/google-gemini-free-vs-paid|publisher=AI Institute|access-date=2025-12-10}}</ref> * Tier แพง ๆ จะได้ใช้รุ่น Pro / Advanced เช่น Gemini 2.5 Pro, 3 Pro, Deep Think ฯลฯ ซึ่ง Google เคลมว่าทำ reasoning / coding ดีกว่าตัวฟรีแบบชัดเจน Android Central<ref>{{cite web|title=Android Central|url=https://www.androidcentral.com/apps-software/ai/google-expands-gemini-3-and-nano-banana-pro-availability-for-ai-mode-in-search|publisher=Android Central|access-date=2025-12-10}}</ref> ===== - เข้า gemini.google.com แบบไม่จ่ายเงิน → ส่วนใหญ่ระบบจะผูกกับรุ่น “ปกติ” (เช่น 2.5 ธรรมดา) ฟีเจอร์บางอย่างหาย / ตัด context / limit เยอะ ===== * เข้า เหมือนเดิมแต่มี AI Pro / Advanced → หลังบ้านจะให้เลือกหรือ auto-route ไปใช้รุ่น Pro/Advanced ที่เก่งกว่า, context ใหญ่กว่า, เครื่องมือเพิ่ม จุดสำคัญ: ถ้าสมมติว่าทั้ง free และ pro เรียก Gemini 2.5 Pro ตัวเดียวกันจริง ๆ ด้วย prompt และ setting เดียวกัน * output ควรจะ “ระดับเดียวกัน” * ไม่มีเกียร์ลับที่เปิดเฉพาะคนจ่ายเงินในตัวโมเดลเดียวกัน คุณภาพมันต่างเพราะ * ฟรี: มักไม่ได้ใช้รุ่นบนสุด / โดนบีบ limit / บางฟีเจอร์ปิด * เสียเงิน: กดใช้รุ่นบน (Pro/Advanced/Deep Think) กับ context/feature เต็ม ๆ ==== ### ==== * ChatGPT มี Free, Plus (~20 USD), Pro, Business, Enterprise ฯลฯ ChatGPT<ref>{{cite web|title=ChatGPT|url=https://chatgpt.com/pricing/|publisher=chatgpt.com|access-date=2025-12-10}}</ref> * Plus/Pro ได้ access ไปยังโมเดลใหม่/แรงกว่า, usage เยอะกว่า, tools เพิ่ม (เช่น Sora, apps/projects ฯลฯ) Zapier<ref>{{cite web|title=Zapier|url=https://chatgpt.com/plans/plus/|publisher=chatgpt.com|access-date=2025-12-10}}</ref> * โมเดลอย่าง GPT-5.1 Instant / Thinking เหล่านี้ rolling out ให้ paid ก่อน แล้วค่อยตามมาที่ free ในภายหลัง OpenAI<ref>{{cite web|title=OpenAI|url=https://openai.com/index/gpt-5-1/|publisher=openai.com|access-date=2025-12-10}}</ref> บางสรุปจากสายรีวิว/เอกสารตอนนี้: * ทั้ง Free กับ Plus สุดท้าย “มีสิทธิ์ได้ใช้ GPT-5.x เหมือนกัน” แต่ - Free: ระบบเลือกให้เอง, limit ต่ำ, ช่วงพีคอาจเด้ง / ตัดให้ใช้รุ่นเล็ก nexos.ai<ref>{{cite web|title=nexos.ai|url=https://nexos.ai/blog/chatgpt-free-vs-paid/|publisher=nexos.ai|access-date=2025-12-10}}</ref> - Plus: เลือกโหมด /รุ่นเองได้มากขึ้น, ได้รุ่น reasoning หนัก ๆ + quota สูงกว่า, priority access เวลาโหลดเยอะ Just AI News<ref>{{cite web|title=Just AI News|url=https://justainews.com/blog/openai-chatgpt-models-explained/|publisher=Just AI News|access-date=2025-12-10}}</ref> ===== - ถ้ามึงใช้ Free แล้วมันบอกว่า “ตอนนี้ใช้ GPT-5.1 Thinking อยู่” แล้วมึงไปใช้ Plus แล้วก็เลือก GPT-5.1 Thinking เหมือนกัน → สมองโมเดลตัวเดียวกัน ตอบก็ต้องระดับเดียวกัน ต่างกันแค่: - paid ถูก throttle น้อยกว่า - ใช้ได้ยาวกว่า / file ใหญ่กว่า / feature เพิ่ม ===== * แต่ในชีวิตจริง - Free มักจะได้ใช้รุ่นท็อป “แบบจำกัด” หรือโดนสลับไปตัวเล็กกว่าตามโหลด - Plus/Pro กดรุ่นท็อปได้สม่ำเสมอ + ได้ของใหม่ก่อน ==== : ==== คำตอบแบบ fact ล้วน: # ถ้าเรียก “โมเดลคนละตัว” - Free → รุ่นกลาง / รุ่นเล็ก - Paid → รุ่น Pro / Advanced / Deep Think / GPT-5.1 Pro ฯลฯ ⇒ ผลลัพธ์ต่างแน่นอน เพราะมันคนละ model capacity กัน # ถ้าเรียก “โมเดลเดียวกันเป๊ะ” (ชื่อเดียว, setting เดียว) - ความเก่งเชิงปัญญา = เท่าเดิม - สิ่งที่เปลี่ยนคือ quota, speed, priority, feature รอบ ๆ ตัวมัน - ไม่มีสวิตช์ลับ “ฉลาดเฉพาะคนจ่ายเงิน” ในตัวเดียวกัน สรุป: จ่าย 20 USD ไม่ได้ไปเพิ่ม IQ โมเดลให้มึงส่วนตัว มันแค่ให้สิทธิ์เข้าถึง รุ่นที่ฉลาดกว่า / ปล่อยให้คิดนานกว่า / ไม่โดนตัดบ่อย และได้ของเล่นเพิ่มเท่านั้น.
Summary:
Please note that all contributions to freem are considered to be released under the Creative Commons Attribution-ShareAlike 4.0 (see
Freem:Copyrights
for details). If you do not want your writing to be edited mercilessly and redistributed at will, then do not submit it here.
You are also promising us that you wrote this yourself, or copied it from a public domain or similar free resource.
Do not submit copyrighted work without permission!
Cancel
Editing help
(opens in new window)