Raphael De Lio
@raphaeldelio.dev
Software Engineer | AI | Machine Learning | Developer Advocacy | International Speaker | Growing @ Redis (@redis.io)
https://raphaeldelio.com | https://youtube.com/raphaeldelio | https://linktr.ee/raphaeldelio
https://raphaeldelio.com | https://youtube.com/raphaeldelio | https://linktr.ee/raphaeldelio
LLMs may get expensive fast. At the same time, vector DBs (eg Redis) are versatile but underutilized
I delivered a talk at JFall yesterday about three strategies that can be implemented with vector DBs to reduce LLM calls. But the truth is that there are many more! #java
github.com/redis-develo...
I delivered a talk at JFall yesterday about three strategies that can be implemented with vector DBs to reduce LLM calls. But the truth is that there are many more! #java
github.com/redis-develo...
November 7, 2025 at 10:44 AM
LLMs may get expensive fast. At the same time, vector DBs (eg Redis) are versatile but underutilized
I delivered a talk at JFall yesterday about three strategies that can be implemented with vector DBs to reduce LLM calls. But the truth is that there are many more! #java
github.com/redis-develo...
I delivered a talk at JFall yesterday about three strategies that can be implemented with vector DBs to reduce LLM calls. But the truth is that there are many more! #java
github.com/redis-develo...
Can artificial intelligence do basic math?
I was listening to Anthropic's recent video "How AI Models Think" based on their research on interpretability and found a few insights very interesting. One for example is that there's evidence that LLMs can do simple math (addition).
I was listening to Anthropic's recent video "How AI Models Think" based on their research on interpretability and found a few insights very interesting. One for example is that there's evidence that LLMs can do simple math (addition).
August 29, 2025 at 12:48 PM
Can artificial intelligence do basic math?
I was listening to Anthropic's recent video "How AI Models Think" based on their research on interpretability and found a few insights very interesting. One for example is that there's evidence that LLMs can do simple math (addition).
I was listening to Anthropic's recent video "How AI Models Think" based on their research on interpretability and found a few insights very interesting. One for example is that there's evidence that LLMs can do simple math (addition).
5/ What if I hadn't set it up? It wouldn't have been catastrophic because I have daily backups. A snapshot of my Redis Instance is stored in Google Cloud Storage every 24 hours. Redundancy is key!
The best part? On Redis Cloud that can all be set up automatically easily. Took me only 10 minutes.
The best part? On Redis Cloud that can all be set up automatically easily. Took me only 10 minutes.
August 27, 2025 at 1:54 PM
5/ What if I hadn't set it up? It wouldn't have been catastrophic because I have daily backups. A snapshot of my Redis Instance is stored in Google Cloud Storage every 24 hours. Redundancy is key!
The best part? On Redis Cloud that can all be set up automatically easily. Took me only 10 minutes.
The best part? On Redis Cloud that can all be set up automatically easily. Took me only 10 minutes.
3/ Luckily, I had set ACL (Access Control List), available since Redis 6.0. Easy to set up and block accounts from running "@dangerous" commands like "FLUSHALL"
August 27, 2025 at 1:54 PM
3/ Luckily, I had set ACL (Access Control List), available since Redis 6.0. Easy to set up and block accounts from running "@dangerous" commands like "FLUSHALL"
1/ "NOPERM User user:209 has no permissions to run the 'flushall' command"
That's the message I got when running "FLUSHALL" on my production Redis instance. 😮💨
My team and I developed an internal platform for us to track our work. The chosen database? Redis, of course.
#redis @redis.io
That's the message I got when running "FLUSHALL" on my production Redis instance. 😮💨
My team and I developed an internal platform for us to track our work. The chosen database? Redis, of course.
#redis @redis.io
August 27, 2025 at 1:54 PM
Vou vender enquanto ainda estou no lucro. Infelizmente não vendi Crocs a tempo
August 15, 2025 at 7:03 AM
Vou vender enquanto ainda estou no lucro. Infelizmente não vendi Crocs a tempo
Coincidentemente fui ao museu militar holandês hoje e vi um cartaz que pedia aos dispensados da primeira guerra para que fossem para casa e não para o bar que isso era melhor para eles e para suas famílias também.
August 10, 2025 at 5:09 PM
Coincidentemente fui ao museu militar holandês hoje e vi um cartaz que pedia aos dispensados da primeira guerra para que fossem para casa e não para o bar que isso era melhor para eles e para suas famílias também.
It’s important to note that GPT-5 doesn’t generate images.
Underlying, it’s still the GPT-Image-1 released in April 2025 model that’s generating the images.
Underlying, it’s still the GPT-Image-1 released in April 2025 model that’s generating the images.
August 9, 2025 at 11:33 PM
It’s important to note that GPT-5 doesn’t generate images.
Underlying, it’s still the GPT-Image-1 released in April 2025 model that’s generating the images.
Underlying, it’s still the GPT-Image-1 released in April 2025 model that’s generating the images.
It’s important to note that GPT-5 doesn’t generate images. Underlying, it’s still the GPT-Image-1 model released in April 2025 that’s generating the images.
August 9, 2025 at 11:19 PM
It’s important to note that GPT-5 doesn’t generate images. Underlying, it’s still the GPT-Image-1 model released in April 2025 that’s generating the images.
I see a lot of people generating images to test GPT-5 capabilities, but it’s important to note that GPT-5 does NOT generate images.
It’s still the GPT-Image-1 model released in April of this year that is generating the images.
It’s still the GPT-Image-1 model released in April of this year that is generating the images.
August 9, 2025 at 11:03 PM
I see a lot of people generating images to test GPT-5 capabilities, but it’s important to note that GPT-5 does NOT generate images.
It’s still the GPT-Image-1 model released in April of this year that is generating the images.
It’s still the GPT-Image-1 model released in April of this year that is generating the images.
It’s important to note that GPT-5 doesn’t generate images. Underlying, it’s still the GPT-Image-1 model that’s generating the images.
August 9, 2025 at 11:01 PM
It’s important to note that GPT-5 doesn’t generate images. Underlying, it’s still the GPT-Image-1 model that’s generating the images.
Deveria era ter vendido a Crocs. Espero que eles comecem a falar de IA para ver se sobe. E eu nunca comprei ou usei um Crocs na vida. Onde eu estava com a cabeça?!
August 8, 2025 at 6:41 PM
Deveria era ter vendido a Crocs. Espero que eles comecem a falar de IA para ver se sobe. E eu nunca comprei ou usei um Crocs na vida. Onde eu estava com a cabeça?!
🚀 GPT-5 is out — and that’s AMAZING news for RAG.
Every time a new model drops, people declare “RAG is dead” because of bigger context windows.
This time they’re also pointing to better accuracy with massive token counts.
Let’s talk about why they’re wrong. 🧵
Every time a new model drops, people declare “RAG is dead” because of bigger context windows.
This time they’re also pointing to better accuracy with massive token counts.
Let’s talk about why they’re wrong. 🧵
August 8, 2025 at 10:51 AM
🚀 GPT-5 is out — and that’s AMAZING news for RAG.
Every time a new model drops, people declare “RAG is dead” because of bigger context windows.
This time they’re also pointing to better accuracy with massive token counts.
Let’s talk about why they’re wrong. 🧵
Every time a new model drops, people declare “RAG is dead” because of bigger context windows.
This time they’re also pointing to better accuracy with massive token counts.
Let’s talk about why they’re wrong. 🧵
mais essa opção mesmo
August 7, 2025 at 10:59 AM
mais essa opção mesmo
Esse é exatamente o ponto. Pesquisadores de AI não tentam mais imitar a inteligência humana da mesma forma que engenheiros aeronáuticos não tentam imitar o voo de um pássaro. Não é esse o objetivo.
A primeira edição do livro é de 1995 btw. A última edição do livro (que estou lendo) é de 2020.
A primeira edição do livro é de 1995 btw. A última edição do livro (que estou lendo) é de 2020.
August 6, 2025 at 11:15 AM
Esse é exatamente o ponto. Pesquisadores de AI não tentam mais imitar a inteligência humana da mesma forma que engenheiros aeronáuticos não tentam imitar o voo de um pássaro. Não é esse o objetivo.
A primeira edição do livro é de 1995 btw. A última edição do livro (que estou lendo) é de 2020.
A primeira edição do livro é de 1995 btw. A última edição do livro (que estou lendo) é de 2020.
A questão é se faz sentido comparar a inteligência de uma AI com a inteligência de um ser humano. É como não aceitar que um avião voa por não voar da mesma forma que um pássaro
Dá uma olhada nessa passagem do livro "Artificial Intelligence: A Modern Approach" Um dos livros mais recomendados no meio
Dá uma olhada nessa passagem do livro "Artificial Intelligence: A Modern Approach" Um dos livros mais recomendados no meio
August 6, 2025 at 10:48 AM
A questão é se faz sentido comparar a inteligência de uma AI com a inteligência de um ser humano. É como não aceitar que um avião voa por não voar da mesma forma que um pássaro
Dá uma olhada nessa passagem do livro "Artificial Intelligence: A Modern Approach" Um dos livros mais recomendados no meio
Dá uma olhada nessa passagem do livro "Artificial Intelligence: A Modern Approach" Um dos livros mais recomendados no meio
A questão é se faz sentido comparar a inteligência de uma AI com a inteligência de um ser humano. É como não aceitar que um avião voa por não voar da mesma forma que um pássaro
Dá uma olhada nessa passagem do livro "Artificial Intelligence: A Modern Approach" Um dos livros mais recomendados no meio
Dá uma olhada nessa passagem do livro "Artificial Intelligence: A Modern Approach" Um dos livros mais recomendados no meio
August 6, 2025 at 10:48 AM
A questão é se faz sentido comparar a inteligência de uma AI com a inteligência de um ser humano. É como não aceitar que um avião voa por não voar da mesma forma que um pássaro
Dá uma olhada nessa passagem do livro "Artificial Intelligence: A Modern Approach" Um dos livros mais recomendados no meio
Dá uma olhada nessa passagem do livro "Artificial Intelligence: A Modern Approach" Um dos livros mais recomendados no meio
Am I the only one getting classic Mac OS X feelings with OpenAI's website graphic designs? I love it by the way.
August 6, 2025 at 5:50 AM
Am I the only one getting classic Mac OS X feelings with OpenAI's website graphic designs? I love it by the way.
It is! Even got the OG controller!
August 3, 2025 at 7:08 AM
It is! Even got the OG controller!
Zelda the wind waker - One of the most beautiful video games I’ve played. Spent a couple of hours playing it today
August 2, 2025 at 4:49 PM
Zelda the wind waker - One of the most beautiful video games I’ve played. Spent a couple of hours playing it today
Weather was better in the afternoon. I usually go for walks with my wife and dog. Just came back from a long one 😃
August 2, 2025 at 4:46 PM
Weather was better in the afternoon. I usually go for walks with my wife and dog. Just came back from a long one 😃
Stack Overflow’s 2025 Developer Survey just dropped, and it’s packed with insights on the state of software development.
Two things stood out to me (especially since I work at Redis) 🧵 cc @redis.io
Two things stood out to me (especially since I work at Redis) 🧵 cc @redis.io
July 29, 2025 at 4:14 PM
Stack Overflow’s 2025 Developer Survey just dropped, and it’s packed with insights on the state of software development.
Two things stood out to me (especially since I work at Redis) 🧵 cc @redis.io
Two things stood out to me (especially since I work at Redis) 🧵 cc @redis.io
It still surprises me how often people talk about LLMs without even mentioning word embeddings. Without embeddings, LLMs wouldn’t even exist.
Hesam Hassani does a fantastic job breaking down what embeddings are (not just technically, but also from a historical perspective) in this article.
Hesam Hassani does a fantastic job breaking down what embeddings are (not just technically, but also from a historical perspective) in this article.
July 29, 2025 at 1:20 PM
It still surprises me how often people talk about LLMs without even mentioning word embeddings. Without embeddings, LLMs wouldn’t even exist.
Hesam Hassani does a fantastic job breaking down what embeddings are (not just technically, but also from a historical perspective) in this article.
Hesam Hassani does a fantastic job breaking down what embeddings are (not just technically, but also from a historical perspective) in this article.
