Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Feb 4 Release Changelogs: - i18n multi-language support - Improved PNL cards and functionality - Limit orders functionality improvements - TWAP orders now continue to execute even when one trade fails - Relay USDC backfill fix - Added ability to get a quote when input is greater than available... show more

Jerry Pan

76,414 subscribers

46,604 views • 9 months ago •via X (Twitter)

Science & Technology Finance

Anya Rossi• Live Now

Private livecam show

31 Comments

Ccxi rou9 months ago

This is one of those products you only understand after using！Come on guys!

9xiner9 months ago

o1~ 尽享丝滑

Zach Prater9 months ago

Bullish on you as a founder 💙

Jerry Pan9 months ago

super early

Zach Prater9 months ago

Im overy here brainstorming a GTM Campaign for @o1_exchange_jp, @o1_exchange_kr and @o1_exchange_cn 👀 Too bullish on @stambouli_o1 to not do something

Jerry Pan9 months ago

@o1_exchange_jp @o1_exchange_kr @o1_exchange_cn 🫡

CoinChaos9 months ago

Been using o1 more lately

Dac vu9 months ago

twap orders fixing failed trades is huge, and those regional accounts lfg

☙ tenitoka ❧(privacy szn)9 months ago

Excellent innovations, they were needed.

ShitGP9 months ago

Bullish! 🚀

DEVETHer9 months ago

Traders will get it looool

币🎭 晟9 months ago

Why did my cashback level change from% 40 to% 35? My points have already exceeded 5000, can the rules be changed arbitrarily?

Jerry Pan9 months ago

There’s no chance of any rate Prob u mixed up your accounts?

币🎭 晟9 months ago

Many people in the Chinese community of the DC discussion forum have changed their cashback level from 40 to 35. It seems that there is a bug in this update, please fix it... I am not the only one doing this

Jerry Pan9 months ago

ok let me check

币🎭 晟9 months ago

Thank you.

Miray Ayas9 months ago

That Jesse buy was clean execution.

mc9 months ago

Long game

Maria Samara9 months ago

This is the kind of changelog real users care about.

john carlo lacaba™♥9 months ago

TWAP not dying on one failed trade is huge.

Sophie9 months ago

Smooth trading keeps you in the zone 🫡

MONOPONSLY9 months ago

@bankrbot Jerry Pan on base

苓绫哒9 months ago

Hello, I came across a rumor on Twitter that your team previously launched a meme coin called $Digimon. I'm wondering if this is true. Is there an AI coin on the Sol chain?

RikuZ9 months ago

Details 👍

AresCode9 months ago

This is the kind of polish that compounds.

she IS FC Queen9 months ago

PNL cards keep getting better every release.

Tik web49 months ago

O1 is keep shipping

Martuz9 months ago

founder自己卷自己 😆

محمد أرحم رازيق مكس🎗️🇺🇲9 months ago

限价单顺多了，舒服

Step In X9 months ago

@stambouli_o1 I shared a quick note via DM. Looking forward to your thoughts.

suryaprakash.base.eth9 months ago

Bro...why did you open 7k worth of betting on the No On-Base token launch by June 30?...🙄🙄

Related Videos

o1 Exchange (o1.exchange) is one of the fastest-growing exchanges on Base. Here's why Jerry Pan chose to build on Base 👇

o1 Exchange (o1.exchange) is one of the fastest-growing exchanges on Base. Here's why Jerry Pan chose to build on Base 👇

Base APAC

32,636 views • 1 month ago

Do you take trading seriously? Use a terminal that does too. o1.exchange brings pro-grade tools to Base like cross-chain support, fast execution, and multi-wallet management. Everything you need in o1 place.

Do you take trading seriously? Use a terminal that does too. o1.exchange brings pro-grade tools to Base like cross-chain support, fast execution, and multi-wallet management. Everything you need in o1 place.

Base

46,987 views • 1 year ago

🚨 OpenAI CEO Sam Altman confirms moving from o1-preview to full o1 model soon " The new reasoning model o1-preview will significantly improve over the coming months when we shift from an initial O1-preview to fully O1 This progress leads creative applications beyond chat interfaces "

🚨 OpenAI CEO Sam Altman confirms moving from o1-preview to full o1 model soon " The new reasoning model o1-preview will significantly improve over the coming months when we shift from an initial O1-preview to fully O1 This progress leads creative applications beyond chat interfaces "

Haider.

114,840 views • 2 years ago

Get started to build on o1.exchange This is a historical bottom for Base based on the sentiment and long-tail asset trading volume. Possibly the worst time to quit Base. If you long crypto, you cannot long Base so the only way to long Base is to build on Base o1.exchange. Launch[.]o1[.]exchange

Get started to build on o1.exchange This is a historical bottom for Base based on the sentiment and long-tail asset trading volume. Possibly the worst time to quit Base. If you long crypto, you cannot long Base so the only way to long Base is to build on Base o1.exchange. Launch[.]o1[.]exchange

Jerry Pan

80,138 views • 3 months ago

OpenAI o1 model coding performance is mindblowing. Today, I built a famous "Chrome Dinosaur Game" in less than 5 minutes. I added a new functionality where the dinosaur bends instead of jumping to avoid birds.

OpenAI o1 model coding performance is mindblowing. Today, I built a famous "Chrome Dinosaur Game" in less than 5 minutes. I added a new functionality where the dinosaur bends instead of jumping to avoid birds.

Haider.

251,465 views • 2 years ago

QwQ is fantastic reasoner and is 10x cheaper than the o1 line We will be combining with o1-mini and o1-preview as part of our route LLM AGI will be an ensemble system that combines the best LLMs to maximize performance, speed and cost

QwQ is fantastic reasoner and is 10x cheaper than the o1 line We will be combining with o1-mini and o1-preview as part of our route LLM AGI will be an ensemble system that combines the best LLMs to maximize performance, speed and cost

Bindu Reddy

26,346 views • 1 year ago

Just combined OpenAI o1 and Cursor Composer to create an iOS app in under 10 mins! o1 mini kicks off the project (o1 was taking too long to think), then switch to o1 to finish off the details. And boom—full Weather app for iOS with animations, in under 10 🌤️ Video sped up!

Just combined OpenAI o1 and Cursor Composer to create an iOS app in under 10 mins! o1 mini kicks off the project (o1 was taking too long to think), then switch to o1 to finish off the details. And boom—full Weather app for iOS with animations, in under 10 🌤️ Video sped up!

Ammaar Reshi

925,207 views • 2 years ago

One effective way to balance cost and quality is to plan larger refactors with o1, and switch to a cheaper model to execute the changes. Live now in our VSCode extension:

One effective way to balance cost and quality is to plan larger refactors with o1, and switch to a cheaper model to execute the changes. Live now in our VSCode extension:

Adam Hofmann

24,711 views • 2 years ago

o1-engineer is here! 🚀 A coding assistant built from the ground up to leverage o1 reasoning capabilities. It can create and edit multiple files or entire folders, plan complex projects, execute them, and write code reviews. All from your terminal 👨‍💻

o1-engineer is here! 🚀 A coding assistant built from the ground up to leverage o1 reasoning capabilities. It can create and edit multiple files or entire folders, plan complex projects, execute them, and write code reviews. All from your terminal 👨‍💻

Pietro Schirano

311,466 views • 2 years ago

my response to #1Challenge oneness [O1]

my response to #1Challenge oneness [O1]

SoaR Vinks

20,011 views • 28 days ago

This is madness... OpenAI o1 model builds a fully functional "chess game" that allows me to compete against an AI-based opponent. o1-preview is the real deal.

This is madness... OpenAI o1 model builds a fully functional "chess game" that allows me to compete against an AI-based opponent. o1-preview is the real deal.

Haider.

633,831 views • 2 years ago

OpenAI o1 answers a famously tricky question for large language models.

OpenAI o1 answers a famously tricky question for large language models.

OpenAI

644,944 views • 2 years ago

🎉Congrats to OpenAI for releasing o1: - Economics: tylercowen asked o1 basically to write a college essay - Genetics: Catherine Brownstein asked o1 to help her reason through "n of 1" cases - medical cases that nobody has ever seen - Physics: Mario Krenn used o1 to draft and reason through complex quantum physics equations - Code: Hongyu Ren prompted a full snake game and it was generated zero shot, working perfectly, and obeyed instructions to add obstacles

🎉Congrats to OpenAI for releasing o1: - Economics: tylercowen asked o1 basically to write a college essay - Genetics: Catherine Brownstein asked o1 to help her reason through "n of 1" cases - medical cases that nobody has ever seen - Physics: Mario Krenn used o1 to draft and reason through complex quantum physics equations - Code: Hongyu Ren prompted a full snake game and it was generated zero shot, working perfectly, and obeyed instructions to add obstacles

swyx @aiDotEngineer CODE

384,828 views • 2 years ago

OpenAI just announced API access to o1 (advanced reasoning model) yesterday. I'm delighted to announce today a new short course, Reasoning with o1, built with OpenAI, and taught by Colin Jarvis, Head of AI Solutions at OpenAI, to show you how to use this effectively! Unlike previous language models which generate output directly, o1 “thinks before it responds,” and generates many reasoning tokens before returning a more thoughtful and accurate response. It is great at complex reasoning -- including planning for agentic workflows, coding, and domain-specific reasoning in STEM fields like law. But how you should use it is quite different from other LLMs. I think o1 will be a game changer for many AI applications; and in this course, you'll learn how to use it effectively. In detail, you’ll: - Learn to recognize what tasks o1 is suited for, and when to use a smaller model, or combine o1 with a smaller model - Understand the new principles of prompting reasoning models: Be simple and direct; no explicit chain-of-thought required; use structure; show rather than tell - Implement multi-step orchestration in which o1 plans, and hands tasks over to gpt-4o-mini to execute specific steps; this illustrates a design pattern to optimize intelligence (accuracy) and cost - Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o - Use o1 for image understanding and learn how it performs better with a "hierarchy of reasoning," in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later - Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you'll iteratively use o1 to modify a prompt to improve performance You'll also learn about how OpenAI used reinforcement learning to produce a model that uses "test-time compute" to improve performance. I think you'll find this course enjoyable and valuable. Please sign up for it here:

OpenAI just announced API access to o1 (advanced reasoning model) yesterday. I'm delighted to announce today a new short course, Reasoning with o1, built with OpenAI, and taught by Colin Jarvis, Head of AI Solutions at OpenAI, to show you how to use this effectively! Unlike previous language models which generate output directly, o1 “thinks before it responds,” and generates many reasoning tokens before returning a more thoughtful and accurate response. It is great at complex reasoning -- including planning for agentic workflows, coding, and domain-specific reasoning in STEM fields like law. But how you should use it is quite different from other LLMs. I think o1 will be a game changer for many AI applications; and in this course, you'll learn how to use it effectively. In detail, you’ll: - Learn to recognize what tasks o1 is suited for, and when to use a smaller model, or combine o1 with a smaller model - Understand the new principles of prompting reasoning models: Be simple and direct; no explicit chain-of-thought required; use structure; show rather than tell - Implement multi-step orchestration in which o1 plans, and hands tasks over to gpt-4o-mini to execute specific steps; this illustrates a design pattern to optimize intelligence (accuracy) and cost - Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o - Use o1 for image understanding and learn how it performs better with a "hierarchy of reasoning," in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later - Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you'll iteratively use o1 to modify a prompt to improve performance You'll also learn about how OpenAI used reinforcement learning to produce a model that uses "test-time compute" to improve performance. I think you'll find this course enjoyable and valuable. Please sign up for it here:

Andrew Ng

358,273 views • 1 year ago

ROUTE LLM - SUPER INTELLIGENCE IN THE MAKING RouteLLM combines the superpowers of o1-preview, Sonnet 3.5, Gemini Flash, o1-mini, 4o, and 4o-mini! Based on your query, it optimizes for latency, cost, and quality of the response. The cool thing about RouteLLM is it combines. - coding ability of Sonnet 3.5 - reasoning ability of o1-preview - hard-coding ability of o1-mini - 1M context of Gemini - speed of 4o-mini Similar to ensemble models that are very effective in classical ML, RouteLLM and similar models will be the most effective in the LLM ecosystem

ROUTE LLM - SUPER INTELLIGENCE IN THE MAKING RouteLLM combines the superpowers of o1-preview, Sonnet 3.5, Gemini Flash, o1-mini, 4o, and 4o-mini! Based on your query, it optimizes for latency, cost, and quality of the response. The cool thing about RouteLLM is it combines. - coding ability of Sonnet 3.5 - reasoning ability of o1-preview - hard-coding ability of o1-mini - 1M context of Gemini - speed of 4o-mini Similar to ensemble models that are very effective in classical ML, RouteLLM and similar models will be the most effective in the LLM ecosystem

Bindu Reddy

66,374 views • 2 years ago

o1-pro is probably the best model i've used for coding, hands down i gave it a pretty complicated codebase and asked it to refactor while referencing docs the difference between claude/gemini/o1 and o1 pro is night and day. first time in a while i've been this impressed. full comparison in the video + code.

o1-pro is probably the best model i've used for coding, hands down i gave it a pretty complicated codebase and asked it to refactor while referencing docs the difference between claude/gemini/o1 and o1 pro is night and day. first time in a while i've been this impressed. full comparison in the video + code.

Sully

255,811 views • 1 year ago