Discover and read the best of Twitter Threads about #GPT
Most recents (24)
My department asked me to give a brief talk about #GPT to them to help folks learn more about what's going on. Here are my #tips in distilled form.
1. Make #GPT part of the classroom. Students know about it, students are using it, bring it into the discussion. Don't pretend it doesn't exist!
2. Take GPT for a test run on your material. How does GPT do answering your questions? Test it on class discussion questions, tests, essays. Get comfortable with what it sounds like but also how your assignments fare in a GPT world.
🐍 #Script en #python para crear contenidos con imágenes y vídeo por #IA en #WordPress con tecnología de #Openai (#GPT)
Mediante un fichero csv generas un contenido por cada keyword adjunta.
Os cuento el proceso que sigue el script👇
(enlace al final del hilo).
Mediante un fichero csv generas un contenido por cada keyword adjunta.
Os cuento el proceso que sigue el script👇
(enlace al final del hilo).
Lo primero que realiza es un análisis de qué es lo que está posicionando en top 10 para la #keyword sobre la que se va a trabajar.
Se revisan los #titles, #descriptions, #h1, #h2, #h3, #h4, #h5 y #h6.
Todo este análisis se hace por separado, y luego se une.
Se revisan los #titles, #descriptions, #h1, #h2, #h3, #h4, #h5 y #h6.
Todo este análisis se hace por separado, y luego se une.
Después de definir la partes principales y la #estructura, se empieza a desarrollar el texto por partes.
Desarrollar el #texto por partes tiene su motivo.
Si le doy la estructura completa a la #IA, responde siempre con un sólo párrafo normalmente.
Desarrollar el #texto por partes tiene su motivo.
Si le doy la estructura completa a la #IA, responde siempre con un sólo párrafo normalmente.
Life is Fast!
We all feel like we never have enough time, so i bring you:
15 Mind-Blowing AI Tools to Revolutionize Your Life and Save You Time!
Let's get to it! 👇
We all feel like we never have enough time, so i bring you:
15 Mind-Blowing AI Tools to Revolutionize Your Life and Save You Time!
Let's get to it! 👇
1. Text Blaze
🔸 Revolutionizing Typing and Automation!
🔸 Say goodbye to repetitive typing and errors with Text Blaze!
#TextBlaze #AITool #Automation #Writing
🔸 Revolutionizing Typing and Automation!
🔸 Say goodbye to repetitive typing and errors with Text Blaze!
#TextBlaze #AITool #Automation #Writing
2. Loopin
🔸 Enhancing Meetings with AI Assistance!
🔸Revolutionize your meetings with Loopin’s AI meeting assistant!
#Loopin #AITool #AIAssistant #AI
🔸 Enhancing Meetings with AI Assistance!
🔸Revolutionize your meetings with Loopin’s AI meeting assistant!
#Loopin #AITool #AIAssistant #AI
Aquí tenéis el hilo de mi consulta de hoy para #GPT:
Prompt:
¿Cómo evaluar el aprendizaje de estudiantes universitarios sin que pueda recibir ayuda de GPT4 o ChatGPT?
#educación #evaluación
Prompt:
¿Cómo evaluar el aprendizaje de estudiantes universitarios sin que pueda recibir ayuda de GPT4 o ChatGPT?
#educación #evaluación
Este tema es de gran interés para los docentes universitarios, que se enfrentan al reto de medir el nivel de conocimiento y competencias de sus alumnos en un contexto de educación a distancia y con la disponibilidad de herramientas de IA cada vez más sofisticadas
Una primera opción es utilizar evaluaciones formativas, es decir, aquellas que tienen como objetivo proporcionar retroalimentación al estudiante sobre su proceso de aprendizaje y orientarlo hacia la mejora.
"Die Firmen wachsen vor allem gegen sich selber. Um zu wachsen, müssen sie sich gegenseitig Marktanteile abnehmen. Außerdem ist @Microsoft wichtig. Fünf Firmen rangeln um die Aufmerksamkeit." (@Westermeyer) #OMR23
🚨Here’s an intuitive explanation for why training on lots and lots of data creates emergent properties, for instance math and reasoning, in large language models like #GPT-4 and #ChatGPT 🚨 1/17
Let’s start with the basics. Real-world data is full of patterns and structure. This structure allows us to describe things with simple rules. We exploit this fact all the time, for example to derive laws of physics or differential equations. 2/17
Complex physical phenomena can be described by surprisingly short mathematical equations. Reasoning and human language also follow rules. All kinds of datasets, from images to text, contain patterns which allow us to compress them. 3/17
#Amazon uruchamia #Bedrock, w 'Wydarzeniach' #Polsat'u mamy specjalistów od #AI, także trend chyba jeszcze nie umiera 😅
Dzisiaj podzielę się z Wami projektami z koszyka #krypto AI które moim zdaniem należy obserwować.
zapraszam na wątek🧵👇
1/20
Dzisiaj podzielę się z Wami projektami z koszyka #krypto AI które moim zdaniem należy obserwować.
zapraszam na wątek🧵👇
1/20
2/20
#graphprotocol
Rzekomo nazywany "#Google'm kryptowalut", to protokół indeksowania umożliwiający przeszukiwanie wiodących blockchainów. Każdy może budować i publikować otwarte interfejsy #API, wywoływać podgrafy, co umożliwia łatwy dostęp do danych.
#graphprotocol
Rzekomo nazywany "#Google'm kryptowalut", to protokół indeksowania umożliwiający przeszukiwanie wiodących blockchainów. Każdy może budować i publikować otwarte interfejsy #API, wywoływać podgrafy, co umożliwia łatwy dostęp do danych.
3/20
#SingularityNET
Celem ogólnym projektu jest umożliwienie konsumentom pozyskiwania usług sztucznej inteligencji od różnych agentów AI na platformie, umożliwiając każdemu dostęp do technologii AI lub uczestnictwo w jej rozwoju.
#SingularityNET
Celem ogólnym projektu jest umożliwienie konsumentom pozyskiwania usług sztucznej inteligencji od różnych agentów AI na platformie, umożliwiając każdemu dostęp do technologii AI lub uczestnictwo w jej rozwoju.
Le gouvernement (service PEReN) a publié un document pédagogique décrivant comme fonctionnent les IA conversationnelles comme ChatGPT #GPT4, en voici une synthèse rapide. 1/9
🧠 Les Large Language Models (LLM) sont d'impressionnants réseaux de neurones qui révolutionnent le Traitement Automatique des Langues (TAL ou NLP). Ce sont des modèles statistiques qui imitent le fonctionnement du cerveau humain pour traiter et comprendre le langage. #NLP 2/9
🏗️ Les réseaux de neurones sont structurés en couches, chaque couche détectant des motifs récurrents (patterns) dans les données. Les neurones contiennent des paramètres qui sont ajustés au cours de l'entraînement pour améliorer les performances. #MachineLearning 3/9
The future of AI: One Super AI Agent or a Symphony of Specialized Agents? 🤖 As we enter a new era of autonomous agents thanks to @yoheinakajima, @SigGravitas, and @LangChainAI, the debate heats up. Let's dive in! 🧵 #GPT
@yoheinakajima @SigGravitas @LangChainAI 2/ The Super AI Agent Hypothesis posits a single, all-powerful AI capable of handling any task. Its primary advantage is simplicity, as users only need to interact with one AI agent, avoiding the need to manage multiple tools or interfaces.
@yoheinakajima @SigGravitas @LangChainAI 3/ But the Super AI Agent Hypothesis faces significant challenges:
a) Technical limitations: immense computational power and advanced algorithms are needed
b) Data access: proprietary data can give specialized AI agents an edge
c) Decentralization & redundancy concerns. #AIrisks
a) Technical limitations: immense computational power and advanced algorithms are needed
b) Data access: proprietary data can give specialized AI agents an edge
c) Decentralization & redundancy concerns. #AIrisks
🤖📚 Descubre las mejores herramientas impulsadas por #AI para la investigación académica y ahorra tiempo para hacer lo que más te gusta
📚 Accede a más información en menos tiempo!
🚀 Dale un impulso a tu investigación académica!
#GPT #DataScience #science #chatGPT #research #ML
📚 Accede a más información en menos tiempo!
🚀 Dale un impulso a tu investigación académica!
#GPT #DataScience #science #chatGPT #research #ML
✅Scispace
Espacio de trabajo para automatizar tareas
Obtén una explicación simple de texto, matemáticas y tablas confusas
Haz preguntas de seguimiento y obtén respuestas instantáneas
Busca papers relevantes
Mejora la colaboración
buff.ly/3gz7LhQ
#Researchtools #science
Espacio de trabajo para automatizar tareas
Obtén una explicación simple de texto, matemáticas y tablas confusas
Haz preguntas de seguimiento y obtén respuestas instantáneas
Busca papers relevantes
Mejora la colaboración
buff.ly/3gz7LhQ
#Researchtools #science
✅Elicit
Automatiza flujos de trabajo
Encuentra papers relevantes sin palabras clave exactas
Resume conclusiones del documento específicas para tu pregunta
Extrae información clave de los documentos
Lluvia de ideas, resumen y clasificación de textos
buff.ly/30DwBok
#GPT4
Automatiza flujos de trabajo
Encuentra papers relevantes sin palabras clave exactas
Resume conclusiones del documento específicas para tu pregunta
Extrae información clave de los documentos
Lluvia de ideas, resumen y clasificación de textos
buff.ly/30DwBok
#GPT4
🧑🏭Le marché du travail à Hong-Kong semble être le plus impacté par l'#IA alors que celui en Inde, le moins... La lecture de l'étude de @GoldmanSachs révèle des graphiques intéressants concernant la disparité des impacts de l'#IA :
🤖 46% des taches réalisées au bureau et dans le domaine administratif, 44% dans le juridique, ou encore 37% dans l'ingénierie peuvent être automatisées, 25% en moyenne et surtout moins de 11% dans la logistique, le transport, la production, l'industrie, le bâtiment, etc.
🤖 My LLM Week 1 & 2 🤖
#gpt4 was only publicly released 14 days ago
Yet, the LLM world is moving really fast, and people are noticing that it's an "iPhone moment"
But if you haven't been able to play catch up, here are the 3 top topics that caught my attention 👇
#gpt4 was only publicly released 14 days ago
Yet, the LLM world is moving really fast, and people are noticing that it's an "iPhone moment"
But if you haven't been able to play catch up, here are the 3 top topics that caught my attention 👇
1/ The paper on jobs impacted by #gpt dropped
🏁 On with S02E01 of my saga for the AI-enabled developer
In this issue, I want to talk a bit about the elephant in the room 🐘
A topic that's not really mentioned for #gpt4's web users cause you need to preserve the magic 🪄
Yep, I'm gonna talk about max context size 👇
1/13
In this issue, I want to talk a bit about the elephant in the room 🐘
A topic that's not really mentioned for #gpt4's web users cause you need to preserve the magic 🪄
Yep, I'm gonna talk about max context size 👇
1/13
☝️ #gpt4 doesn't remember everything
Have you heard of 8K and 32K contexts?
Apart from pricing 💸, do you know what it really entails?
It means that your chat actually has a short-term memory 😶
2/13
Have you heard of 8K and 32K contexts?
Apart from pricing 💸, do you know what it really entails?
It means that your chat actually has a short-term memory 😶
2/13
If you are a #gpt pro user, have you noticed that it keeps forgetting rules from time to time?
And have you noticed that the longer the messages & response, the faster it seems to forget?
Well, that's because of context limitations
3/13
And have you noticed that the longer the messages & response, the faster it seems to forget?
Well, that's because of context limitations
3/13
[JUST IN] LLM Superpowers are now in @opera! 🤯
Contextual #AI prompts, sidebar integrations of #GPT-based services, and cutting-edge generative #AI tools are now available in your Opera browser! 🔥
Contextual #AI prompts, sidebar integrations of #GPT-based services, and cutting-edge generative #AI tools are now available in your Opera browser! 🔥
The new #AI option can be tricky to find, so I have created a quick video that shows you how to do it!
🏁 Like a plumber would say, "Let's-a-go" with part 5
This time, I'll focus a bit more on the development side cause that may be why you've come here in the first place 😗
1/13
This time, I'll focus a bit more on the development side cause that may be why you've come here in the first place 😗
1/13
#chatgpt's been great to pop up new projects (albeit some outdated methods once in a while)
But now that we're getting to the meat of software making, which is actually more than following a gettin' started page, a couple of things are happening
Time for numbering #️⃣
2/13
But now that we're getting to the meat of software making, which is actually more than following a gettin' started page, a couple of things are happening
Time for numbering #️⃣
2/13
1️⃣ I need to provide more context more often
Yep, the large data set it's been trained on is not enough. Now it needs to be aware of local context which means:
🔸 Reminding it of folder structure
🔸 Giving files content
🔸 Giving dependencies content
🔸 Fetching it doc
3/13
Yep, the large data set it's been trained on is not enough. Now it needs to be aware of local context which means:
🔸 Reminding it of folder structure
🔸 Giving files content
🔸 Giving dependencies content
🔸 Fetching it doc
3/13
New paper on #GPT4 & "Labor Market Impact" is out.
It's an early evaluation, but creatives should be paying attention to this ... 👀
🧵 1/5
It's an early evaluation, but creatives should be paying attention to this ... 👀
🧵 1/5
All the jobs that show 0 exposure to being automated by LLMs are defined by
- blue-collar, manual labor
- outdoor or non-office
- lower educational requirements
- use of specialized tools or equipment
As we'll see: jobs /w higher educational requirements ➡️ high exposure 🚨 2/5
- blue-collar, manual labor
- outdoor or non-office
- lower educational requirements
- use of specialized tools or equipment
As we'll see: jobs /w higher educational requirements ➡️ high exposure 🚨 2/5
🏁 On with Part 4 of my #gpt4 saga
Between pricing (I'm cheap as f😵k) and rate limiting, I'm now spending half my time writing
Truth is, I quite enjoy it so let's gooooo 👇
1/15
Between pricing (I'm cheap as f😵k) and rate limiting, I'm now spending half my time writing
Truth is, I quite enjoy it so let's gooooo 👇
1/15
So at least the #GPT4's API is available for prompting.
But I don't like the playground
👶🏻 I need pairprog-webview, nextjs, tailwind to chat with your own API
🤖 Sure thing
👵🏻 Wow, this API call looks quite outdated and doesn't work
🤖 ermmm...
How do I solve this? 🤔
2/15
But I don't like the playground
👶🏻 I need pairprog-webview, nextjs, tailwind to chat with your own API
🤖 Sure thing
👵🏻 Wow, this API call looks quite outdated and doesn't work
🤖 ermmm...
How do I solve this? 🤔
2/15
Open up platform.openai.com/docs/api-refer…
Copy, paste into @euangoddard ✨magnificent✨ "Paste as markdown page", copy back, paste to #gpt4
👶🏻 Here's the updated doc
🤖 K boss
✂️ > 📋 > ▶️
✨ It works ✨
3/15
Copy, paste into @euangoddard ✨magnificent✨ "Paste as markdown page", copy back, paste to #gpt4
👶🏻 Here's the updated doc
🤖 K boss
✂️ > 📋 > ▶️
✨ It works ✨
3/15
I'm on an adventure to get #gpt4 to code its own VSCode extension 🗺
Starting from scratch with Language Models, I'll share every discovery, insight, or rambling that crosses my mind along the way.
So, if you're interested, here's a link to every part 👇
Starting from scratch with Language Models, I'll share every discovery, insight, or rambling that crosses my mind along the way.
So, if you're interested, here's a link to every part 👇
1️⃣ The honeymoon part
In which I start my journey and quickly diverge into publishing a full website using mostly #gpt4 prompts
In which I start my journey and quickly diverge into publishing a full website using mostly #gpt4 prompts
2️⃣ Leaning into prompts
In which I make the mistake of continuing my part 1 thread and quickly diverge into some insights about #gpt4 prompting, and the parallels to standards in #leanengineering
In which I make the mistake of continuing my part 1 thread and quickly diverge into some insights about #gpt4 prompting, and the parallels to standards in #leanengineering
Is GPT-4 intelligent enough to solve ARC (github.com/fchollet/ARC)- a collection of intelligence tests devised by @fchollet? I ran a few quick experiments to check.
#gpt4 #gpt #ai #ml
#gpt4 #gpt #ai #ml
In this test, the solution is to output the portion of the grid containing a different coloured cell. Thus the answer to the right-hand side question would be a 6x6 blue grid containing a red cell at the second position in the fourth row down.
GPT-4 did provide a smaller grid containing the correct colours (1 and 2). However, it generated a 5x5 blue grid with one red cell in it that was obviously in the wrong place. Not correct, but the gist of its answer was along the right tracks.
We love what @jacksonfall has been doing with #HustleGPT so we’re doing our own crypto edition!
The lowdown: We’ve given #GPT4 a budget of $100. We’ve instructed it to make as much money as possible.
Can GPT-4 navigate the choppy crypto waters and stay green?
A thread 🧵
The lowdown: We’ve given #GPT4 a budget of $100. We’ve instructed it to make as much money as possible.
Can GPT-4 navigate the choppy crypto waters and stay green?
A thread 🧵
To get it up to speed, we fed GPT all of our Markets News stories over 7 days, a selection of our most viewed stories over the same period, plus a round-up of 2021 and 2022. Here’s what #GPT4 thinks.
上次介绍了12个我常用的加密货币领域的工具产品。其中包含：链上数据，加密研究报告，地址跟踪，IDO信息，代币解锁，代币估值等。
最近朋友问我，如何高效获得加密Alpha资讯，世界财经新闻。这次我将介绍2个秘密武器。👇
最近朋友问我，如何高效获得加密Alpha资讯，世界财经新闻。这次我将介绍2个秘密武器。👇
2.高效推特管理软件。我看推特是这样，不知道您是否一样？
A-这个工具可以把您关注的推特列表，横向展示
B-每个推特列表上都有一个搜索按钮，对感兴趣的项目，可在专门的列表中搜索，比如最近 #AI 二层出来一个项目 #GPT ，我在项目深度研究列表中，便很快搜索到了机会
tweetdeck.twitter.com
A-这个工具可以把您关注的推特列表，横向展示
B-每个推特列表上都有一个搜索按钮，对感兴趣的项目，可在专门的列表中搜索，比如最近 #AI 二层出来一个项目 #GPT ，我在项目深度研究列表中，便很快搜索到了机会
tweetdeck.twitter.com
all my friends who read a lot when young are successful now
i think reading is probably the more important thing you can do in elementary school
if ur brain is like an LLM, you should maximize the # of tokens it sees while training
i think reading is probably the more important thing you can do in elementary school
if ur brain is like an LLM, you should maximize the # of tokens it sees while training
i read so much in elementary school that writing is very easy for me. i liken it to next token prediction.
SAT/ACT grammar came very easy for me, i just went off of what sounded right. idioms as well, even though my family isn't native english speaker. but id read all them
SAT/ACT grammar came very easy for me, i just went off of what sounded right. idioms as well, even though my family isn't native english speaker. but id read all them
