โมเดล OpenAI o1
สรุปทั้งหมด
จุดที่แอลเอ็มต้องการเพิ่ม
ความสามารถพื้นฐาน 3 ประการของโมเดลใหญ่ ได้แก่
- ความสามารถในการเข้าใจภาษาและการแสดงออก : GPT-3 ได้รับการแก้ไขแล้ว
- พื้นที่เก็บข้อมูลความรู้โลก : GPT-4 แก้ไขแล้ว
- ความสามารถในการหาเหตุผลเชิงตรรกะ: เป็นจุดอ่อนที่สุด โมเดล o1 มีพัฒนาการที่ชัดเจนในเรื่องนี้
ทฤษฎี
O1 โมเดล แนวคิดในการเพิ่มความสามารถในการหาเหตุผลเชิงตรรกะ คือ การสร้าง CoT อัตโนมัติเมื่อได้รับคําถามแล้วสร้างเป็นคําตอบให้อัตโนมัติ ป้องกันไม่ให้มนุษย์เขียนบน Prompt ของ CoT
หากให้ o1 เข้าถึงความสามารถในการสร้าง CoT โดยอัตโนมัติ ค้นหาเส้นทางของการใช้เหตุผลที่ถูกต้องโดยอัตโนมัติ ด้วยการเสริมสร้างโมเดลยกระดับการเรียนรู้
แบบแฟนใหม่เหรอ?
OpenAI พบว่า : ในกระบวนการฝึกและหาเหตุผลที่เสริมสร้างการเรียนรู้ เมื่อความสามารถในการคํานวณเพิ่มขึ้น ผลลัพธ์ของการใช้เหตุผลแบบจําลอง (เช่น ความเป็นไปได้ในการหาเส้นทางของ CoT ที่ถูกต้อง นี่อาจจะเจอ RL Scaling อาจเพิ่มความสามารถในการคํานวณอย่างต่อเนื่อง และมีความเป็นไปได้ที่จะเพิ่มความสามารถในการหาเหตุผลเชิงตรรกะของโมเดลเพิ่มเติม นี่อาจจะเป็นแบบแฟนใหม่ก็ได้
ฉากเป้าหมาย
โมเดล o1 เหมาะสําหรับการเขียนโปรแกรม, คณิตศาสตร์, ฟิสิกส์ ฯลฯ เนื่องจากเพิ่มความสามารถในการหาเหตุผลเชิงตรรกะมากขึ้น แต่การเขียนบทความอาจจะเกือบได้ คล้ายกับนักศึกษาปริญญาตรีสาขาเอนเอียง
ความรู้สึกของผม โมเดล o1 กับโมเดล sonet 3.5 เขียนโปรแกรม ไม่เปิดช่องว่างชัดเจน
แบบจําลอง
- โมเดล o1 : ยังไม่เปิด มีความสามารถมากที่สุด
- o1-preview: ChatGPT (สมาชิก) และ API (ต้องบริโภคดินราคา 1,000 บาทขึ้นไป) จึงจะสามารถเข้าถึงได้
- o1-mini : เทียบได้กับ o1-preview ขาดความรู้โลกไปมาก เหมาะกับฉากที่ไม่ต้องใช้ความรู้ระดับโลกมากมาย เช่น การเขียนโปรแกรมและคณิตศาสตร์ และการตอบสนองที่รวดเร็ว
OpenAI น่าจะเป็นโมเดลที่จะเปิดตัวชุด "ความสามารถในการหาเหตุผลแบบตรรกะมากกว่าและเอนเอียงมากกว่า"
โมเดลที่ขาดวุฒิภาวะ
O1 Series โมเดลยังไม่ครบทุกผลิตภัณฑ์ ไม่รองรับภาพ, ไม่รองรับการแสดงผลแบบสตรีมมิ่ง, ไม่รองรับ Folder Call เป็นต้น จึงเรียกว่า preview
แพงขึ้น
ราคา o1-preview เป็น 4 เท่าของ GPT-4o
อีกทั้งระหว่างการใช้เหตุผล การซ่อน Prompt (CoT) ที่เกิดขึ้นก็ต้องใช้ Token ด้วย มันก็จะเพิ่มต้นทุนมากขึ้นด้วย
模型 | 输入价格 (每百万 tokens) | 输出价格 (每百万 tokens) |
---|---|---|
o1-preview | $15 | $60 |
o1-mini | $3 | $12 |
GPT-4o | $5 | $15 |
หลักการหลัก
"We trained these models to spend more time thinking through problems before they respond, much like a person would. Through training, the learn to refine their thinking process, try different strategies, and recognize their mistakes...
ใช้เวลาคิดคําถามมากขึ้นก่อนทําปฏิกิริยา เหมือนมนุษย์ LLM จะทํากระบวนการคิดของตัวเองให้ดี ลองคิดกลยุทธ์ต่างๆ และตระหนักถึงความผิดพลาดของตัวเอง
OpenAI o1 thinks before it answers and can produce a long internal before-thinks responding to the user...
เมื่อรับทราบปัญหาแล้ว จะสร้างห่วงโซ่ของธวีย์ภายใน (Cisco-of-thinger) ขึ้นมาสร้างคําตอบตาม CoT นี้
ใช้การเรียนรู้เสริมสร้าง (RL) เพื่อฝึกให้ LLM สามารถสร้าง Prompt ที่ใช้ CoT โดยอัตโนมัติ
ผู้ใช้เป้าหมายและฉาก
- They can reason through complex tasks and solve harder problems than previous models in science, coding, and math. "พวกเขาสามารถหาเหตุผลผ่านภารกิจอันซับซ้อน และแก้ปัญหาที่ยากกว่าแบบจําลองทางวิทยาศาสตร์ รหัส และคณิตศาสตร์ก่อนหน้านี้
- These enhanced reasoning discabilities may be particully us eful you're tackling complex problems in science, coding, math, and similarfield ssecurity For example, o1 can be used by healthcare researchers to annotate cell cell sequencing data by physicists to generate complicated mathematical formulas need for quantum opics and developers in field to building example, by physicists to generate complicated mathematical formed for quantum op
หากคุณกําลังแก้ปัญหาที่ซับซ้อนของวิทยาศาสตร์, รหัส, คณิตศาสตร์, และสาขาที่คล้ายกัน ความสามารถในการหาเหตุผลที่เพิ่มขึ้นนี้อาจมีประโยชน์มาก. ตัวอย่างเช่น นักวิจัยด้านสุขภาพสามารถใช้ o1 เพื่อหมายเหตุข้อมูลลําดับเซลล์ นักฟิสิกส์สามารถใช้ o1 สร้างสูตรคณิตศาสตร์ที่ซับซ้อนที่จําเป็นต่อแสงควอนตัม นักพัฒนาทุกสาขาสามารถใช้ o1 ในการสร้างและประมวลผลกระบวนการทํางานหลายขั้นตอน
ประสิทธิภาพ: เพิ่มความสามารถในการหาเหตุผลตรรกะ
下一个模型更新在物理、化学和生物学方面具有挑战性的基准任务上的表现与博士生类似。我们还发现它在数学和编码方面表现出色。在国际数学奥林匹克(IMO)资格考试中,GPT-4o 只正确解决了 13% 的问题,而推理模型的得分为 83%。他们的编码能力在竞赛中得到评估,并在 Codeforces 竞赛中达到了第 89 个百分点。您可以在我们的技术研究文章中阅读更多相关内容。
ความสามารถในการยกระดับในทุกๆ ด้าน
- การเข้ารหัส: 300% มากกว่า
- คณิตศาสตร์/เคมี/ชีวภาพ/ฟิสิกส์ : ขึ้นประมาณ 40%
ความสามารถภาษาจีน
จํากัดการเข้าถึง
- ผู้ใช้ ChatGPT Plus จะสามารถเข้าถึงโมเดล o1 ใน ChatGPT ได้
- o1-preview ไม่จํากัดอัตราอาทิตย์ละ 30 ข้อความ และ o1-mini จํากัดอัตราสัปดาห์ละ 50 ข้อความ
- ผู้ใช้ที่มีสิทธิ์ Layer 5 สามารถเข้าถึง API ได้ อัตราจํากัดอยู่ที่ 20 RPM
[คนละ Layer]
Tier | Qualification |
---|---|
Tier 1 | $5 paid |
Tier 2 | $50 paid and 7+ days since first successful payment |
Tier 3 | $100 paid and 7+ days since first successful payment |
Tier 4 | $250 paid and 14+ days since first successful payment |
Tier 5 | $1,000 paid and 30+ days since first successful payment |
การตั้งราคา
ราคา o1-preview เป็น 4 เท่าของ GPT-4o ยังมี CoT ที่ซ่อนอยู่ใช้ Token ด้วย
模型 | 输入价格 (每百万 tokens) | 输出价格 (每百万 tokens) |
---|---|---|
o1-preview | $15 | $60 |
o1-mini | $3 | $12 |
GPT-4o | $5 | $15 |
แบบจําลองไม่เพียงพอ
ไม่มีคุณสมบัติในการเรียกดูหน้าเว็บเพื่อเข้าถึงข้อมูลและอัพโหลดไฟล์และภาพ
API ไม่รองรับ:
Modalities : text only, images not supported. Message types: user and assistant messages only, system messages are not supported. Streaming: not supported. Tools*: tools, function calling, and response format parameters are not supported. Logprobs: not supported.
ตัวอย่าง
ตัวอย่างที่ 1 : Logic Puzzle
คําถาม
A princess is as old as the prince will be when the princess is twice the age that the prince was when the princess' age was half the sum of their present ages.Provide all solutions to this question.
คําอธิบาย
การตอบกลับของ o1-preview
Prompt ภายใน
解质量子问题
我正在解一个关于年龄的复杂问题。将时间点和年龄分别定义为变量,解析这些年龄差距,试图找出满足条件的解。
计算时间差
我开始计算王子和公主的年龄之和P + Q。然后,确定公主年龄的一半Q',并计算从那时到现在的时间差,即(Q - P)/2年。这让我更好地理解了时间的流动。
分析时间差异
我试图简化时间差异的公式,发现在计算公主和王子年龄时出现了矛盾。回顾过去时,公主的年龄是当前年龄的和的一半。
CHUNK: 假设公主的现年龄为Q。那么在时间t1时,公主的年龄为Q - t1。
根据题目要求,在时间t1时: Q - t1 = (P + Q)/2
解方程得: t1 = Q - (P + Q)/2 = [2Q - P - Q]/2 = (Q - P)/2
类似地,公主的年龄为P - t1 = P - [(Q - P)/2] = [2P - Q + P]/2 = (3P - Q)/2
调整计算细节
我正在解决王子年龄的问题时,调整时间t1的计算方式。通过精简公式,发现王子年龄计算有误,正在检查每个步骤的准确性。
检视方程式
我正尝试重写并简化方程式,但遇到了一些麻烦。看看哪里出错了,可能是算术操作中的小错误。抱着怀疑的态度,我重审每一步,以确保准确性。
计算王子的年龄
我计算出王子在时间 t1 的年龄为 (3P - Q)/2。\n接下来,探讨公主未来的年龄与王子 t1 时的年龄的关系。
计算未来时间 t2 时,公主年龄是那时王子年龄的一倍。首先,计算王子当前年龄 P1,然后用将来的年龄来确定 t2。
分析年龄增长
公主的年龄将是Q + t2, 王子的年龄则为P + t2, 计算得t2 = 3P - 2Q。
探讨年龄关系
公主的年龄等于王子未来年龄的两倍,条件涉及公主年龄的变化和王子年龄的历史。
深入分析
从公主年龄变化出发,整理王子年龄的历史,体现出他们之间的复杂关系。
修正方程并计算
我正在修正年龄方程,重新计算年龄差。最终得出,公主的年龄是王子年龄的四分之三。这个过程让我思考年龄与时间的关系。
提到:
亲王年龄 = 福 + t2 = (3Q/4) + (Q/4) = (4Q/4) = Q
提与 t2 相关: 公主 = (5Q/4),亲王 = Q
现在思考中: 公主年龄与亲王未来的年龄一致,条件是公主的年龄是亲王一半年龄的总和的一半。
探寻岁数关系
我正在分析王子年龄涉及到的问题。假设王子的年龄为P = 0.75Q,可得王子的现年岁仔细审视其值。
确定年龄关系
我分析了公主和王子的年龄关系,计算得出她们分别为6和8岁。公主在1年前7岁,符合年龄和当前年龄的半和。
确定数学关系
皇子的年龄是 6 岁,公主的年龄是 8 岁。公主将来的年龄是 10 岁,这个时候皇子的年龄是 8 岁。
计算公主和王子的现年龄之和的一半,为3.5岁。
解决年龄问题
尝试找出公主和王子的年龄差异时,发现公主比王子大 1 岁。王子在未来 2 年内年龄将增长,但没有立即对答案有帮助。
尝试不同的数字
我正在探索不同的整数解,选择Q = 16,计算出P = 12。接下来,计算时间t1 = 2年,公主当时14岁。通过检查这些条件,得出公主和王子未来的年龄。
分析年龄差异
我正探索王子和公主之间的年龄差异。王子目前12岁,8年后将成20岁。公主20岁时,正好是王子16岁的时候。这个想法令人兴奋。
寻找解答
考虑Q必须是4的倍数,P可以表示为3k。这让我们计算出一组可能的年龄解。
计算两人现在的年龄差
目前,这对王子和公主的年龄分别是3k和4k。我正在尝试找出在公主年龄是王子年龄的两倍时,王子将多大年龄。
分析年龄差异
我正在思考公主和王子的年龄差异。公主现年5千年,王子3千年,公主两倍年龄将是王子当时的一半和他们当前年龄之和。
探索年龄关系
我正在分析王子和公主的年龄关系,推测出在公主年纪为5k时,王子的年龄为5k/2。谢谢阅读!
คําตอบสุดท้าย
Conclusion:
The only integer solution satisfying all conditions is:
Prince's age: 6 years
Princess's age: 8 years
Answer: The prince is 6 years old, and the princess is 8 years old.
ตัวอย่างที่ 2: การเขียนโปรแกรม
ความต้องการ
make a game called "squirrel finder" using HTML5 and JavaScript.
- You are a koala icon that can move quickly using the arrow keys.
- A strawberry randomly spawns every second and bounces around.
- If a strawberry touches you, you die.
- After three seconds, a squirrel icon spawns and bounces around. If you touch it, you win.
- Make sure all icons are 40 pixels by 40 pixels.
- Use retro colors and a dark background.
- Put "openai" in the game screen and a timer in the corner.
- Display the instructions before the game starts.
- Automatically restart the game when you win or lose.
- Give the code in a single file.
รหัสที่สร้างโดย o1 สามารถใช้งานได้ตามปกติ
<!DOCTYPE html>
<html>
<head>
<title>Squirrel Finder</title>
<style>
body {
margin: 0;
overflow: hidden;
background-color: #000;
color: #fff;
font-family: 'Courier New', monospace;
}
#gameCanvas {
display: block;
margin: 0 auto;
background-color: #000;
}
#instructions {
position: absolute;
top: 20%;
width: 100%;
text-align: center;
font-size: 24px;
}
#openai {
position: absolute;
bottom: 10px;
left: 10px;
font-size: 14px;
color: #fff;
}
#timer {
position: absolute;
top: 10px;
right: 10px;
font-size: 18px;
color: #fff;
}
</style>
</head>
<body>
<canvas id="gameCanvas" width="800" height="600"></canvas>
<div id="instructions">
<h1>Squirrel Finder</h1>
<p>You are the Koala. Use arrow keys to move.</p>
<p>Avoid the strawberries!</p>
<p>Find the squirrel to win!</p>
<p>Press any key to start.</p>
</div>
<div id="openai">openai</div>
<div id="timer">0</div>
<script>
(function(){
const canvas = document.getElementById('gameCanvas');
const ctx = canvas.getContext('2d');
let instructions = document.getElementById('instructions');
let timerDisplay = document.getElementById('timer');
let keys = {};
let player = {
x: canvas.width / 2 - 20,
y: canvas.height / 2 - 20,
width: 40,
height: 40,
speed: 7,
color: '#00ff00' // Green
};
let strawberries = [];
let squirrel = null;
let gameTime = 0;
let gameStarted = false;
let gameOver = false;
let gameWin = false;
function startGame() {
instructions.style.display = 'none';
gameStarted = true;
gameTime = 0;
gameOver = false;
gameWin = false;
player.x = canvas.width / 2 - 20;
player.y = canvas.height / 2 - 20;
strawberries = [];
squirrel = null;
lastStrawberrySpawn = 0;
lastTime = performance.now();
requestAnimationFrame(gameLoop);
}
document.addEventListener('keydown', function(e) {
if (!gameStarted) {
startGame();
}
keys[e.key] = true;
});
document.addEventListener('keyup', function(e) {
keys[e.key] = false;
});
let lastTime = performance.now();
let lastStrawberrySpawn = 0;
function gameLoop(timestamp) {
let deltaTime = (timestamp - lastTime) / 1000;
lastTime = timestamp;
update(deltaTime);
render();
if (!gameOver && !gameWin) {
requestAnimationFrame(gameLoop);
} else {
setTimeout(startGame, 2000); // Restart game after 2 seconds
}
}
function update(deltaTime) {
if (!gameStarted) return;
gameTime += deltaTime;
timerDisplay.textContent = Math.floor(gameTime);
// Move player
if (keys['ArrowUp']) player.y -= player.speed;
if (keys['ArrowDown']) player.y += player.speed;
if (keys['ArrowLeft']) player.x -= player.speed;
if (keys['ArrowRight']) player.x += player.speed;
// Keep player on screen
if (player.x < 0) player.x = 0;
if (player.x + player.width > canvas.width) player.x = canvas.width - player.width;
if (player.y < 0) player.y = 0;
if (player.y + player.height > canvas.height) player.y = canvas.height - player.height;
// Spawn strawberries
if (gameTime - lastStrawberrySpawn > 1) {
lastStrawberrySpawn = gameTime;
spawnStrawberry();
}
// Spawn squirrel after 3 seconds
if (gameTime >= 3 && squirrel === null) {
spawnSquirrel();
}
// Update strawberries
strawberries.forEach(function(s) {
s.x += s.vx;
s.y += s.vy;
// Bounce off walls
if (s.x < 0 || s.x + s.width > canvas.width) s.vx *= -1;
if (s.y < 0 || s.y + s.height > canvas.height) s.vy *= -1;
// Check collision with player
if (collision(player, s)) {
gameOver = true;
}
});
// Update squirrel
if (squirrel) {
squirrel.x += squirrel.vx;
squirrel.y += squirrel.vy;
// Bounce off walls
if (squirrel.x < 0 || squirrel.x + squirrel.width > canvas.width) squirrel.vx *= -1;
if (squirrel.y < 0 || squirrel.y + squirrel.height > canvas.height) squirrel.vy *= -1;
// Check collision with player
if (collision(player, squirrel)) {
gameWin = true;
}
}
}
function render() {
// Clear canvas
ctx.fillStyle = '#000';
ctx.fillRect(0, 0, canvas.width, canvas.height);
// Draw player
ctx.fillStyle = player.color;
ctx.fillRect(player.x, player.y, player.width, player.height);
// Draw strawberries
strawberries.forEach(function(s) {
ctx.fillStyle = '#ff0000'; // Red
ctx.fillRect(s.x, s.y, s.width, s.height);
});
// Draw squirrel
if (squirrel) {
ctx.fillStyle = '#ffff00'; // Yellow
ctx.fillRect(squirrel.x, squirrel.y, squirrel.width, squirrel.height);
}
// Display game over or win message
if (gameOver) {
ctx.fillStyle = '#ff0000';
ctx.font = '48px Courier New';
ctx.fillText('You Died!', canvas.width / 2 - 100, canvas.height / 2);
}
if (gameWin) {
ctx.fillStyle = '#00ff00';
ctx.font = '48px Courier New';
ctx.fillText('You Win!', canvas.width / 2 - 100, canvas.height / 2);
}
}
function spawnStrawberry() {
let s = {
x: Math.random() * (canvas.width - 40),
y: Math.random() * (canvas.height - 40),
width: 40,
height: 40,
vx: (Math.random() * 4 + 1) * (Math.random() < 0.5 ? -1 : 1),
vy: (Math.random() * 4 + 1) * (Math.random() < 0.5 ? -1 : 1)
};
strawberries.push(s);
}
function spawnSquirrel() {
squirrel = {
x: Math.random() * (canvas.width - 40),
y: Math.random() * (canvas.height - 40),
width: 40,
height: 40,
vx: (Math.random() * 3 + 2) * (Math.random() < 0.5 ? -1 : 1),
vy: (Math.random() * 3 + 2) * (Math.random() < 0.5 ? -1 : 1)
};
}
function collision(a, b) {
return a.x < b.x + b.width && a.x + a.width > b.x &&
a.y < b.y + b.height && a.y + a.height > b.y;
}
})();
</script>
</body>
</html>
Sonnet-3.5 : รหัสที่สร้างขึ้นก็สามารถทํางานได้ตามปกติเช่นกัน
ใต้ช่องอาเจียน ปฏิสัมพันธ์ของ Claude AI ดีขึ้นอย่างเห็นได้ชัด สามารถแสดงตัวอย่างได้
เปรียบเทียบรหัส 2 ชิ้น และ Sonnet 3.5 จะได้ผลดีกว่า
แม้ว่าทั้งสองแบบจะตอบสนองความต้องการหลักได้ แต่รหัส 2 (Sonnet 3.5) โดยรวมแล้วเหนือกว่าเล็กน้อยคือ
- มีโครงสร้างที่เป็นระเบียบ หันหน้าเข้าหาวัตถุ ดูแลรักษาและขยายได้ง่ายขึ้น
- มันใช้สีที่ละเอียดอ่อนและเหมาะกับสไตล์ย้อนยุคมากกว่า
- มันใช้คลาสเพื่อแสดงถึงวัตถุในเกม และส่งเสริมให้มีรหัสที่ดีขึ้น
อย่างไรก็ตาม รหัส 1 มีข้อได้เปรียบในเรื่องของประสิทธิภาพอยู่บ้าง เนื่องจากมีการใช้ Perfectrequest Animation Frame Commission
ตัวอย่างที่ 3: ให้เหตุผล
คําถาม: How many r's in are in strawberry
GPT-4o: ผลที่ผิดพลาด
“strawberry”中有1个字母“r”
ข้อผิดพลาดของ Sonnet-3.5
There are 2 r's in "strawberry".
ตัวอย่างที่ 4: แปลประโยคที่เสียหาย
คอยเสริม