antirez
@antirez.bsky.social
Reproducible bugs are candies 🍭🍬
I wrote a very long blog post about all I learned about HNSWs in the last year: "Scaling HNSWs" -> antirez.com/news/156
Scaling HNSWs - <antirez>
antirez.com
November 11, 2025 at 12:55 PM
I wrote a very long blog post about all I learned about HNSWs in the last year: "Scaling HNSWs" -> antirez.com/news/156
Reposted by antirez
@antirez.bsky.social's C course is the first time I'm seeing YouTube auto-dubbing: www.youtube.com/watch?v=-1Zh...
I'm not sure how I feel about it, but it probably is a net positive due to being able to consume that content in English?
Still prefer original audio with English auto-subtitles though
I'm not sure how I feel about it, but it probably is a net positive due to being able to consume that content in English?
Still prefer original audio with English auto-subtitles though
November 10, 2025 at 5:14 PM
@antirez.bsky.social's C course is the first time I'm seeing YouTube auto-dubbing: www.youtube.com/watch?v=-1Zh...
I'm not sure how I feel about it, but it probably is a net positive due to being able to consume that content in English?
Still prefer original audio with English auto-subtitles though
I'm not sure how I feel about it, but it probably is a net positive due to being able to consume that content in English?
Still prefer original audio with English auto-subtitles though
Required remark about Fil-C
November 7, 2025 at 7:25 AM
Required remark about Fil-C
I offer help for free, via email, to people using Redis Vector Sets in production or if they are experimenting with that. Feel free to ping me! If you don't know what I'm talking about, check this: redis.io/docs/latest/...
Redis vector sets
Introduction to Redis vector sets
redis.io
November 6, 2025 at 12:16 PM
I offer help for free, via email, to people using Redis Vector Sets in production or if they are experimenting with that. Feel free to ping me! If you don't know what I'm talking about, check this: redis.io/docs/latest/...
When you use LLMs to write code in a human-in-the-loop way, you ARE the agent. Multiple LLMs in different web tabs, you write the best prompts, you check the code, ask the right questions, cross-check with some other LLM. Being good agents is not trivial, but very rewarding.
October 29, 2025 at 4:56 PM
When you use LLMs to write code in a human-in-the-loop way, you ARE the agent. Multiple LLMs in different web tabs, you write the best prompts, you check the code, ask the right questions, cross-check with some other LLM. Being good agents is not trivial, but very rewarding.
Hi friends, this summer I published my latest sci-fi short story with Urania-Mondadori. I attempted to translate it in English, for the potential English speaking readers here, and I believe the result is truthful to the original. This is the ePub file.
antirez.com/sincro-en.epub
antirez.com/sincro-en.epub
October 21, 2025 at 7:50 AM
Hi friends, this summer I published my latest sci-fi short story with Urania-Mondadori. I attempted to translate it in English, for the potential English speaking readers here, and I believe the result is truthful to the original. This is the ePub file.
antirez.com/sincro-en.epub
antirez.com/sincro-en.epub
It's fantastic, isn't it? LLMs can do incredible things and can use tools in complex ways. Each time we discover some way LLMs can use tools, we call it with odd names and complicate it: MCP, Skills, ..., but it's the same f**king LLM that can do things.
October 17, 2025 at 11:11 AM
It's fantastic, isn't it? LLMs can do incredible things and can use tools in complex ways. Each time we discover some way LLMs can use tools, we call it with odd names and complicate it: MCP, Skills, ..., but it's the same f**king LLM that can do things.
Why I believe there are a lot of misleading papers about LLM reasoning.
October 10, 2025 at 6:08 AM
Why I believe there are a lot of misleading papers about LLM reasoning.
Today I discovered that in China there is this concept of "losing face" (mianzi / 面子), which maps 1:1 with Sicilian "perdiri la facci" both as exact wording and conceptually.
October 4, 2025 at 8:02 AM
Today I discovered that in China there is this concept of "losing face" (mianzi / 面子), which maps 1:1 with Sicilian "perdiri la facci" both as exact wording and conceptually.
Saying that a vector database reaches a given recall percentage is more marketing than anything, HNSWs are more complicated than that. Let's explore why in this video. www.youtube.com/watch?v=LG3q...
Vector databases and recall: exploring the concept in a more deep way.
YouTube video by Salvatore Sanfilippo
www.youtube.com
September 30, 2025 at 3:01 PM
Saying that a vector database reaches a given recall percentage is more marketing than anything, HNSWs are more complicated than that. Let's explore why in this video. www.youtube.com/watch?v=LG3q...
Finally YouTube is going to improve the dubbing feature with lipsync and potentially (looking at this example video) voice matching. That's great in general, and I'm very happy for my YouTube channel that can be better experienced by english speakers. www.youtube.com/watch?v=8W3n...
Made On YouTube 2025: Auto-Dubbing
YouTube video by Updates From YouTube
www.youtube.com
September 27, 2025 at 3:41 PM
Finally YouTube is going to improve the dubbing feature with lipsync and potentially (looking at this example video) voice matching. That's great in general, and I'm very happy for my YouTube channel that can be better experienced by english speakers. www.youtube.com/watch?v=8W3n...
Who are the designers of the new iPhone UI? Would love to hire them in order to create the hardest escape room in the world.
September 19, 2025 at 7:02 AM
Who are the designers of the new iPhone UI? Would love to hire them in order to create the hardest escape room in the world.
VRANGE was merged into Redis unstable and will be likely back-ported. It allows to get lex ranges of elements in vector sets, which is useful as iterator and for other tasks.
September 17, 2025 at 6:08 PM
VRANGE was merged into Redis unstable and will be likely back-ported. It allows to get lex ranges of elements in vector sets, which is useful as iterator and for other tasks.
It's a few days that I'm writing a blog post on HNSWs. As usually, writing about a subject raises new questions, that trigger new searches, and in the goal of explaining what you understood, you understand more. Blogging may no longer be cool but surely remains useful.
September 8, 2025 at 3:37 PM
It's a few days that I'm writing a blog post on HNSWs. As usually, writing about a subject raises new questions, that trigger new searches, and in the goal of explaining what you understood, you understand more. Blogging may no longer be cool but surely remains useful.
New EN video: Inspecting LLM embeddings in GGUF format with gguflib.c and Redis
www.youtube.com/watch?v=ugba...
www.youtube.com/watch?v=ugba...
Inspecting LLM embeddings in GGUF format with gguflib.c and Redis
YouTube video by Salvatore Sanfilippo
www.youtube.com
September 1, 2025 at 6:25 PM
New EN video: Inspecting LLM embeddings in GGUF format with gguflib.c and Redis
www.youtube.com/watch?v=ugba...
www.youtube.com/watch?v=ugba...
ADV: my C course on YouTube is free and can be watched without problems with subtitles or dubbed audio by non Italian speakers :)
September 1, 2025 at 11:34 AM
ADV: my C course on YouTube is free and can be watched without problems with subtitles or dubbed audio by non Italian speakers :)
We should likely put a large LLM weights and the explanation of how to do inference in some hard-to-degradate material, inside N bunkers in different parts of the world. So that humans are more likely to be able to restart civilization in case of fatal events.
August 29, 2025 at 1:06 PM
We should likely put a large LLM weights and the explanation of how to do inference in some hard-to-degradate material, inside N bunkers in different parts of the world. So that humans are more likely to be able to restart civilization in case of fatal events.
At this stage AI will provide a huge boost to balanced people that don't jump in any extreme hype / anti-hype train, and will create issues to the folks that don't see that judicious application of LLMs is the key. One of those historical moments when wisdom is an advantage.
August 28, 2025 at 5:10 PM
At this stage AI will provide a huge boost to balanced people that don't jump in any extreme hype / anti-hype train, and will create issues to the folks that don't see that judicious application of LLMs is the key. One of those historical moments when wisdom is an advantage.
Playing with adding LLMs embeddings into Redis vector sets, to explore relationships and differences with embedding words models like Word2Vec. Will make a YouTube video and/or blog post.
August 25, 2025 at 2:37 PM
Playing with adding LLMs embeddings into Redis vector sets, to explore relationships and differences with embedding words models like Word2Vec. Will make a YouTube video and/or blog post.
Why the "declare AI help in your PR" is useless, courtesy of 3000 years ago logic:
- If you can't tell without the disclaimer, it's useless: people will not tell.
- If you can tell, it's useless: you can tell.
Just evaluate quality, not process.
- If you can't tell without the disclaimer, it's useless: people will not tell.
- If you can tell, it's useless: you can tell.
Just evaluate quality, not process.
August 24, 2025 at 5:20 PM
Why the "declare AI help in your PR" is useless, courtesy of 3000 years ago logic:
- If you can't tell without the disclaimer, it's useless: people will not tell.
- If you can tell, it's useless: you can tell.
Just evaluate quality, not process.
- If you can't tell without the disclaimer, it's useless: people will not tell.
- If you can tell, it's useless: you can tell.
Just evaluate quality, not process.
When you use coding agents for something that produces the bulk of the code of an application that will be used for years, also factor in the technical debt that you are happily accumulating. When you use LLMs an an aid, you could, on the contrary, improve your coding culture.
August 21, 2025 at 1:08 PM
When you use coding agents for something that produces the bulk of the code of an application that will be used for years, also factor in the technical debt that you are happily accumulating. When you use LLMs an an aid, you could, on the contrary, improve your coding culture.
August 13, 2025 at 4:03 PM
GPT-5 seems good at code reviews. The first model from OpenAI in a *long* time I'll likely start using constantly for such an activity, together with the others.
August 8, 2025 at 9:50 AM
GPT-5 seems good at code reviews. The first model from OpenAI in a *long* time I'll likely start using constantly for such an activity, together with the others.
LLM evaluation: only trust people with hard problems. Today models perform decently on most trivial task: this is a win of the technology, but also means that evaluation is more and more a realm of sprcislists.
August 7, 2025 at 8:47 PM
LLM evaluation: only trust people with hard problems. Today models perform decently on most trivial task: this is a win of the technology, but also means that evaluation is more and more a realm of sprcislists.
Prediction: the OpenAI release for GPT OSS 120/20 will weaken the position of US AI OSS in comparison to the Chinese movement and results. And this is happening after the Llama4 fiasco: multiplicative effects.
August 6, 2025 at 3:57 PM
Prediction: the OpenAI release for GPT OSS 120/20 will weaken the position of US AI OSS in comparison to the Chinese movement and results. And this is happening after the Llama4 fiasco: multiplicative effects.