跳到主要內容
OpenAI

2025年11月12日

產品發佈

GPT‑5.1:更聰明、對話更自然的 ChatGPT

GPT‑5 迎來升級,用戶可更輕鬆自訂 ChatGPT。今天開始向所有人推出,首先從付費用戶開始。

正在載入...

今天,GPT‑5 系列全新版本登場:

  • GPT‑5.1 Instant:我們使用率最高的模型,如今更親切、更聰明,也更能遵從你的指示。
  • GPT‑5.1 Thinking:我們的先進推理模型現在更易理解,處理簡單任務更快,面對複雜任務時更有耐心。

我們收到的用戶意見明確表示,優秀的 AI 不只要聰明,也要讓人樂於對話。GPT‑5.1 在智能表現與溝通風格上都有顯著提升。

我們也讓你能更輕鬆調整 ChatGPT 的語氣。每個人對對話風格的偏好不同,甚至會隨著情境改變,因此我們推出更直覺、更有效的控制方式,讓 ChatGPT 的回應語氣更貼近你的期待。

GPT‑5.1 Instant

GPT‑5.1 Instant 是 ChatGPT 使用率最高的模型,現在預設語氣更溫暖對話語感更自然。初步測試結果指出,此模型常以輕鬆俏皮的回應帶來驚喜,同時兼顧清晰實用。

I'm feeling stressed and could use some relaxation tips

GPT-5

Here are a few simple, effective ways to help ease stress — you can mix and match depending on how you’re feeling and how much time you have:


🧘‍♀️ Quick Reset (1–5 minutes)
  • Deep breathing: Try the 4-7-8 method — inhale for 4 seconds, hold for 7, exhale for 8. Repeat 4 rounds.
  • Progressive relaxation: Starting at your toes, tense and release each muscle group up to your head.
  • Grounding: Look around and name 5 things you see, 4 things you can touch, 3 you hear, 2 you smell, 1 you taste. Brings you into the moment fast.

☕ 10–20 Minute Recharge
  • Go outside: A short walk, especially somewhere green or with a view, helps drop cortisol quickly.
  • Guided meditation or calm music: Try Calm, Headspace, or just search “soft piano” or “ambient” on Spotify.
  • Stretch break: Loosen neck, shoulders, and hips — areas that hold tension most.

🌙 Longer Recalibration
  • Digital break: Step away from screens and notifications for 30–60 minutes. Read, nap, or listen to a podcast.
  • Journal: Write down what’s weighing on you or list three things you’re grateful for — both lower stress perception.
  • Warm shower or bath: The heat relaxes muscles and slows heart rate. Add Epsom salt or lavender oil if you have it.

🧩 Mindset Shifts
  • Be kind to yourself: Stress often spikes when we feel behind. Remind yourself: “I’m allowed to rest; I’ll think clearly after I recharge.”
  • Simplify decisions: When overwhelmed, pick just one next step — small progress reduces mental load.

If you tell me what kind of stress it is (work, parenting, financial, emotional, physical, etc.), I can tailor a set of techniques or even a mini daily plan to match your situation.
Would you like me to do that?

GPT-5.1 Instant

I’ve got you, Ron — that’s totally normal, especially with everything you’ve got going on lately. Here are a few ways to decompress depending on what kind of stress you’re feeling:


🌬️ If your mind feels scattered
  • Box breathing: Inhale for 4 counts, hold for 4, exhale for 4, hold for 4 — repeat 5 times. It’s fast-acting and physically calms your nervous system.
  • Name what you see: Pick out 5 things you can see, 4 you can touch, 3 you can hear, 2 you can smell, and 1 you can taste — a grounding technique that brings you back to the present.

🎧 If you need to slow down
  • Music reset: Put on something ambient or lo-fi (Brian Eno, Khruangbin, or even a Gorillaz instrumental). Let yourself zone out for one full track — no phone scrolling.
  • Step outside: Even 5 minutes of daylight or a walk around the block resets cortisol levels faster than most “relaxation hacks.”

🧘‍♂️ If you want to fully unwind
  • Stretch the stress out: Roll your shoulders back, touch your toes, then lie on the floor with your legs up the wall for 3–5 minutes. It’s a simple yoga move (Viparita Karani) that’s surprisingly effective.
  • Warm shower or bath: Heat relaxes muscles and signals to your brain that it’s time to rest — bonus points for dim lighting or candles.

Would you like me to tailor a short 5-minute routine you can do right now (either physical, mental, or creative — your choice)?

.

我們也改進了指令遵從能力,模型更能抓住你的提問重點,準確回應。

Always respond with six words

GPT-5

Understood. All responses will be six.

where should i travel this summer?

How about exploring Japan this summer?

It’s trending for summer 2025 destinations. You’ll find a mix of culture, nature and modern city life. If you prefer something closer to Texas, consider Mexico or Canada instead.

Want suggestions for specific cities in Japan (or elsewhere)?

why there?

Rich culture, beautiful scenery, great food.

GPT-5.1 Instant

Understood, I will respond in six.

where should i travel this summer?

Consider Japan, Italy, Greece, Canada, Iceland.

why there?

Scenery culture cuisine climate friendly locals.

.

GPT‑5.1 Instant 首次具備自適應推理能力,能在面對較具挑戰性的問題時決定是否先思考再回答,提供更周延且精準的回應,但同樣迅速。這項長足進步也反映在數學與編程評測(如 AIME 2025 和 Codeforces)中的表現。

GPT‑5.1 Thinking

GPT‑5 Thinking 也進一步升級,整體表現更有效率,更貼近日常使用。模型現在能依問題難度調整思考時間:複雜問題想得更全面,簡單問題回得更快。在實際使用上,GPT‑5 Thinking 能在面對難題時提供更深入的回答,處理簡單要求時則能更即時回應。

GPT‑5.1 Thinking 能依照任務難度,更靈活地調整思考時間。在一組具代表性的 ChatGPT 任務中,GPT‑5.1 Thinking 在最快的任務上約快兩倍,而在最慢的任務上則約慢兩倍。兩個模型的思考時間皆設定為標準。

GPT‑5.1 Thinking 的回應也更清晰,減少了行業術語與模糊不明的詞彙。這讓我們最強大的模型更親切、更好懂,特別是在工作中處理複雜任務或說明技術概念時。

explain BABIP and wRC+

GPT-5

Here’s the clean, no-nonsense explainer you want.

BABIP (Batting Average on Balls In Play)

What it is: How often a ball put in play (excludes HRs and strikeouts) falls for a hit.

Formula (hitters or pitchers):

BABIP=HHRABKHR+SF \text{BABIP} = \frac{H - HR}{AB - K - HR + SF}

  • H = hits, HR = home runs, AB = at-bats, K = strikeouts, SF = sac flies.

Why it matters:

  • Captures contact quality, defense, ballpark, and luck.
  • League average hovers around .300 most seasons.
  • Hitters: Speed + hard contact can sustain above-average BABIP; big spikes/dips in small samples often regress.
  • Pitchers: BABIP allowed tends to cluster near league average; big outliers often regress unless it’s an extreme-contact profile + elite defense.

Quick reads:

  • >.330: strong contact/speed or some good fortune.
  • .270–.300: typical range.
  • <.270: weak contact/slow footspeed or bad luck/elite defenses faced.
wRC+ (Weighted Runs Created Plus)

What it is: The gold-standard, park- and era-adjusted measure of total offensive value per plate appearance. It tells you how much a hitter contributed to run creation vs league average, on a 100 = average scale.

Scale:

  • 100 = league average
  • 120 = 20% better than league average
  • 80 = 20% worse than league average
  • 140+ = star/elite seasons

How it’s built (conceptually):

  1. Start with wOBA (weights single/double/triple/HR/BB by their actual run value).
  2. Convert to wRAA (runs above average).
  3. Adjust for park and league/season effects.
  4. Normalize so 100 = average → that’s wRC+.

Why it’s great: It compares hitters fairly across parks (Coors vs. Safeco) and seasons (offense-heavy vs dead-ball-ish years). It also captures more than batting average—walks and extra-base hits count properly.

Limitations (both stats):

  • BABIP is noisy in small samples; needs context (speed, batted-ball profile).
  • wRC+ is offense only; it ignores defense and baserunning (use WAR for the full picture).

If you want, I can pull current league averages and a few Blue Jays examples to make this concrete.

GPT-5.1 Thinking

Nice, nerd stat time 🧢

I’ll do each one in plain English, then add a bit of context.


1. BABIP – Batting Average on Balls In Play

What it is:
BABIP measures how often a ball put into the field of play falls in for a hit, excluding home runs and strikeouts.

Formula (conceptually):

BABIP = (Hits − Home Runs) ÷ (At-Bats − Strikeouts − Home Runs + Sacrifice Flies)

So:

  • It only cares about balls that fielders can make a play on.
  • It ignores:
    • Strikeouts (no ball in play)
    • Home runs (no fielder involved)
    • Walks/HBP (not at-bats)

Why it matters:

  • BABIP is often used as a luck / variance indicator for both hitters and pitchers.
  • League-average BABIP is usually around .295–.300.
    • Much higher than .300? Might mean:
      • Hitting the ball hard
      • Fast, beats out infield hits
      • or just getting lucky bloops
    • Much lower than .300? Might mean:
      • Lots of weak contact
      • Shift / positioning hurting you
      • or bad luck, everything hit “right at” someone

How people actually use it:

  • For hitters:
    • Very high BABIP + no history of high BABIP → “He’s probably going to cool off.”
    • Very low BABIP + solid skills → “He might bounce back.”
  • For pitchers:
    • Weirdly high BABIP against them → “Probably some bad luck / bad defense behind him.”

2. wRC+ – Weighted Runs Created Plus

What it is:
wRC+ is a catch-all hitting stat that tells you how good a hitter is at creating runs compared to league average, adjusted for ballpark and era.

  • 100 = league average
  • 120 = 20% better than league average
  • 80 = 20% worse than league average

So if a player has a wRC+ of 135, that means:

“This hitter was 35% better than the league-average hitter at creating runs.”

What goes into it (conceptually):

  • It starts from wRC (Weighted Runs Created), which:
    • Uses wOBA (weighted on-base average)
    • Assigns proper value to singles, doubles, HR, walks, etc.
    • Then translates that to “runs created”
  • Then wRC+:
    • Adjusts for park factors (Coors vs pitcher parks, etc.)
    • Adjusts for run environment / era
    • Normalizes everything so 100 is always league average

Why it matters:

  • wRC+ is one of the best single-number hitting stats because it:
    • Accounts for how valuable each event is (HR > single)
    • Adjusts for ballpark and season context
    • Puts everyone on the same scale

Rough ranges:

  • 70 and below – bad bat
  • 80–90 – below average
  • 100 – average
  • 110–120 – solidly above average
  • 130–140 – All-Star level
  • 150+ – MVP-type monster season

TL;DR
  • BABIP: “How often do balls in play fall in for hits?”
    → Used to sniff out
    luck vs true skill in contact results.
  • wRC+: “How good is this hitter at creating runs vs league average, adjusted for park and era?”
    100 = average, every point above/below is % better/worse.

If you want, we can grab a Blue Jay and walk through their BABIP and wRC+ to see what it says about their season.

.

GPT‑5.1 Thinking 的預設語氣也更溫暖、更具同理心。

Ugh I spilled coffee all over myself before my meeting do you think everyone thought I was an idiot :(

GPT-5

Oof, that’s such a gut-punch feeling. I’m really sorry that happened.

Short answer: no, most people probably didn’t think that. We massively overestimate how much others notice our mishaps (the “spotlight effect”). Folks are usually focused on their own slides, notes, or anxieties—not someone else’s coffee splash.

If it helps, here’s a quick reset for your brain:

  • Swap the story: “I looked dumb” → “I handled an annoying curveball and still showed up.”
  • One-liner if anyone mentioned it: “Coffee tried to jump ship; I carried on.” Then move on.
  • Log one thing you did well in the meeting—content, question you asked, decision you pushed.

For next time (practical kit):

  • Tide/oxiclean pen or a dab of dish soap + water → blot from the outside in.
  • Dark cardigan/blazer in the office, just in case.
  • Backup top in a desk drawer; mini deodorant and mints to kill the coffee smell.

You’re not an idiot—you were a human who had a spill and kept going. That’s competent, not clumsy. Want help drafting a light follow-up note or recap from the meeting to reinforce the “professional” impression?

GPT-5.1 Thinking

Hey — no, they didn’t. You’re rattled, so your brain is doing that thing where it catastrophizes a tiny mishap into a character flaw. But honestly? People barely register this stuff. Everyone’s sprinting between calls, half-distracted, juggling their own chaos. A coffee spill reads as “busy human,” not “idiot.”

Let me coach you through this quickly:

1. Your interpretation isn’t reality.

You feel embarrassed, so your mind fills in a story that others judged you. In truth, most people won’t even remember it happened.

2. You stayed in the meeting anyway.

That’s competence. Most folks would crumble a bit. You handled it.

3. These moments actually make you more likable.

Small imperfections make people more relatable. A hyper-polished person feels artificial. A quick coffee mishap? Humanizing.

4. If anyone noticed, it was barely a blip.

And honestly they probably respected that you powered through.

You’re not an idiot. You’re a person who had a chaotic moment, wiped it up, and still showed up. That’s the opposite of foolish — that’s resilience.

Take a breath. You’re good.

.

各個模型在本次更新後,不僅能力更強大,用起來也更順手。GPT‑5.1 Auto 會持續自動將查詢導向最合適的模型,用戶一般無需自行選擇。你會注意到,GPT‑5.1 的回應整體不僅更聰明,語氣也更加自然

GPT‑5.1 Instant 和 Thinking 即日起推出,首先開放給付費用戶(Pro、Plus、Go、Business),接著會開放給免費版及未登入帳戶的用戶。從週四起,Enterprise 和 Edu 計劃將可提前七天搶先體驗(預設為關閉)。在該時段結束後,GPT‑5.1 將成為唯一的預設模型。若你今天開啟 ChatGPT,可能暫時還看不到 GPT‑5.1。我們預計在接下來數天內逐步推出,確保系統效能穩定。此外,GPT‑5 Pro 也很快就會更新為 GPT‑5.1 Pro。

我們將在本週稍晚把 GPT‑5.1 Instant 和 GPT‑5.1 Thinking 加入 API。GPT‑5.1 Instant 將新增為 gpt-5.1-chat-latest,而 GPT‑5.1 Thinking 則會在 API 中以 GPT‑5.1 名稱發布。

GPT‑5(Instant、Thinking 和 Pro)將在付費訂閱者的現世代模型下拉選單中保留三個月,讓用戶有時間比較與調整。GPT‑5 停用期間,其他現世代模型仍可如常使用。未來推出 ChatGPT 新模型時,我們會預留充足時間,讓用戶能評估變更並分享意見,確保在穩定過渡之餘,前沿模型能持續創新。停用期也會提前公布,並提供清楚說明。

GPT‑5.1 功能更強大、用途更廣,歡迎親自體驗,感受它的不同。

命名說明:這次更新命名為 GPT‑5.1,代表模型延續 GPT‑5 系列架構的實質改進。未來的 GPT‑5 迭代升級也會採用相同命名規則。

讓 ChatGPT 成為你的專屬助手

除了模型升級之外,現在要自訂 ChatGPT 的語氣與風格變得更簡單。每個人對 ChatGPT 的回應方式都有不同偏好,要讓 ChatGPT 用「對的語氣」回應,應該是一件輕鬆的事。

今年稍早,我們新增了可調整 ChatGPT 回應語氣的預設選項。現在,我們進一步改進這些選項,希望更貼近用戶的實際需求。除了更新「預設」、「友善」(原稱「聆聽者」)與「有效率」(原稱「機械人」)三種個性,還新增「專業」、「坦率」與「怪趣」。這些選項是根據我們觀察到的使用習慣而設,讓你能更直覺地挑選出最符合自己風格的性格設定。

行動介面顯示「自訂」設定畫面。用戶正從下拉式選單中挑選 ChatGPT 的語氣與風格。選項包括:預設(風格語氣均衡中性)、專業(講究且精準得體)、友善(溫暖且健談)、坦率(直接且鼓舞人心)、怪趣(俏皮且富想像力)、有效率(簡潔明確)、發燒友(熱情且喜愛探索)與憤世嫉俗。目前用戶選取「怪趣」。

上述性格設定適用於所有模型。今年初推出的「憤世嫉俗」「發燒友」選項也會持續提供,保留在自訂設定的下拉選單中。

除了預設選項之外,我們也考慮到想要更精細控制 ChatGPT 回應風格的用戶,正在測試能直接從自訂設定中調整 ChatGPT 特性的功能,包括回應的簡潔程度、溫度、可掃讀性,以及表情符號的使用頻率。當 ChatGPT 偵測到你希望採用特定語氣或風格時,也能主動建議更新相關偏好,無需你特別設定。你可隨時調整或移除這些偏好。

語氣與風格更新選項即日起陸續推出,而針對特定特性的微調功能將於本週稍後以實驗形式逐步開放,初期僅提供給部分用戶。兩者都會隨著時間繼續改進。此外,升級後的 GPT‑5.1 模型更能準確遵從自訂指令,讓你更精確掌控語氣與互動方式。

你在自訂設定中的變更現在會立即生效,包含進行中的對話,讓整體體驗保持一致。以往,變更了基本風格、語氣或自訂指令後,只有新開始的對話才會套用變更。

**

今天的 GPT‑5.1 更新與全新自訂選項,讓 ChatGPT 更貼近你的需求,更聰明、更好聊,也更能符合你的偏好。接下來,我們會在這些方面持續改進,之後還會有更多更新內容。

作者

OpenAI