I start with a high level design md doc which an AI helps write. Then I ask another AI - whether the same model without the context, or another model - to critique it and spot bugs, gaps and omissions. It always finds obvious in hindsight stuff. So I ask it to summarize its findings and I paste that into the first AI and ask its opinions. We form an agreed change and make it and carry on this adversarial round robin until no model can suggest anything that seems weighty.
I then ask the AI to make a plan. And I round robin that through a bunch of AIs adversarially as well. In the end, the plan looks solid.
Then the end to end test cases plan and so on.
By the end of the first day or week or month - depending on the scale of the system - we are ready to code.
And as code gets made I paste that into other AIs with the spec and plan and ask them to spot bugs, omissions and gaps too and so on. Continually using other AI to check on the main one implementing.
And of course you have to go read the code because I have found it that AI misses polishes.
The discourse around AI is that we’ve unlocked a whole new unsupervised paradigm of development; but you’re basically describing how Google has built code for a decade, just with humans of different levels of trust instead of AI.
And I’m not saying that to poke fun at you (my workflow is essentially identical to yours), or at Google, but rather to say that there’s nothing new :)
AI is a fantastic accelerator of effective and ineffective workflows alike. It’s showing us which are effective and ineffective on way shorter timescales / in realtime!
Thanks for adding this. Excited about array/regex, also very interested in your experience using LLMs to stretch your abilities. There are many of us laboring quietly on various projects attempting the same. "Vibe coding" (and the backlash) doesn't really capture how we work.
> He is not "your avg dev" and it took him 4 months with llm.
To clarify, from TFA:
> even before LLMs the implementation was likely something I could do in four months. What changed is that in the same time span, I was able to do a lot more
The initial timeframe was 4 months, he was able to do more work within the same timeframe with LLMs.
Thanks for the write up. Always interesting to see how very senior developers interact with AI these days.
@antirez: Introducing a regex feature that late into the project for a seemingly unrelated feature feels a bit weird? Can you explain more your rationale on that? thanks!
Once I realized arrays were a great fit for text files, many use cases I could conceive were always limited by the fact we need to grep on files. So I thought: what is the AROP equivalent for files? ARGREP. Then I made sure to add both fast, exact and regexp matching so that depending on the use case the best tool could be used. I then discovered that for many OR-ed strings regexps could be the faster way if we'll optimized. And then I specialized TRE a bit.
Closely matches my own experiences with current SOTA AI. Extremely useful collaborator, far from being a replacement for human intelligence and creativity.
LLMs are the insensitive Asmovian robots I’ve always wanted, who translate and do the hardest part of my job: ensuring my emails are polite and none of my true thoughts or feelings are revealed…
Now I just need a way to protect my chats from any potential discovery, and <pew pew> business’ll be easy.
I occasionally type into slack "Future lawyers, the previous conversation is a joke. No one is doing cocaine to get through writing requirements docs."
We have a “don’t get the slack subpoenaed” emoji that gets frequent use. Incidentally, a lawyer doing discovery in the future could just search for uses of that emoji to find what they’re looking for.
There are projects that I develop mostly not looking at the code, but owning the concepts, algorithms and ideas asking questions and giving hints, and owning especially the product. But, not for Redis, not yet at least. When in the future this will be possible, server software, the way it is developed today, will be over. I bet there will be still projects and repositories, as accumulation of features, fixes and experiences will still be worth it, but the role of programmers will be very similar to what Linus did so far for the kernel. And for certain projects I'm developing, like the DeepSeek v4 inference engine, I'l already working like that.
It feels like Redis is becoming a small database, which seems to make it more convenient to use. Could you add more examples that clarify where the boundary should be?
Well, Redis is a data structures server, and has very complicated and edgy data structures like the HyperLogLog, so I have very little doubts that a fundamental data type like the Array will fit :) Also the actual complexity added is mostly two C files that are quite commented and understandable.
Sure there are also the AOF / RDB glues, the tests, the vendored TRE library for ARGREP. But all in all it's self contained complexity with little interactions with the rest of the server.
A quick note: if we focus only on that part of the implementation, skipping tests and persistence code which is not huge, 4075 lines in 4 months are an average of 33 lines per day, which is quite low.
I’m a big fan of your work, and I honestly didn’t expect to receive a reply from you. Thank you.
Also, thank you for pointing out exactly where I was misunderstanding the issue.
In the past, I used Redis for temperature measurements in a smart farm project. I used Hashes back then, but it seems like Array would fit that use case much better.
This looks like a very useful feature. Thank you again for the reply.
- the project essentially spans almost 3 different (albeit minor) generations of LLMs. Have you noticed major differences in their personas, behavior, output for that specific use case?
- when using AI for feedback, have you ever considered giving it different "personalities"? I have few skills that role play as very different reviewers with their own different (by design conflicting) personalities. I found this to improve the output, but also to be extremely tiring and to often have high noise ratio.
- when did you, if ever, felt that AI was slowing you down massively compared to just doing it yourself (e.g. some specific bug or performance or design fix)? Are there recurring patterns?
- conversely, how often did AI had moments where it genuinely gave you feedback or ideas that would've not come to you?
- last: do you have specific prompts, skills, setups, etc to work on specific repositories?
Sharing my current MO:
I start with a high level design md doc which an AI helps write. Then I ask another AI - whether the same model without the context, or another model - to critique it and spot bugs, gaps and omissions. It always finds obvious in hindsight stuff. So I ask it to summarize its findings and I paste that into the first AI and ask its opinions. We form an agreed change and make it and carry on this adversarial round robin until no model can suggest anything that seems weighty.
I then ask the AI to make a plan. And I round robin that through a bunch of AIs adversarially as well. In the end, the plan looks solid.
Then the end to end test cases plan and so on.
By the end of the first day or week or month - depending on the scale of the system - we are ready to code.
And as code gets made I paste that into other AIs with the spec and plan and ask them to spot bugs, omissions and gaps too and so on. Continually using other AI to check on the main one implementing.
And of course you have to go read the code because I have found it that AI misses polishes.
The discourse around AI is that we’ve unlocked a whole new unsupervised paradigm of development; but you’re basically describing how Google has built code for a decade, just with humans of different levels of trust instead of AI.
And I’m not saying that to poke fun at you (my workflow is essentially identical to yours), or at Google, but rather to say that there’s nothing new :)
AI is a fantastic accelerator of effective and ineffective workflows alike. It’s showing us which are effective and ineffective on way shorter timescales / in realtime!
How much faster/slower are you with that process compared to writing code yourself?
Thanks for adding this. Excited about array/regex, also very interested in your experience using LLMs to stretch your abilities. There are many of us laboring quietly on various projects attempting the same. "Vibe coding" (and the backlash) doesn't really capture how we work.
Let's make it very clear - this is the original creator of redis, or one of them.
He is not "your avg dev" and it took him 4 months with llm.
This is not a seal of approval for you to go and command all your developers to move to Claude code/codex/any other ai coding tool fully.
I'm looking at you - any avg CEO of a startup.
> He is not "your avg dev" and it took him 4 months with llm.
To clarify, from TFA:
> even before LLMs the implementation was likely something I could do in four months. What changed is that in the same time span, I was able to do a lot more
The initial timeframe was 4 months, he was able to do more work within the same timeframe with LLMs.
It's a pretty strong endorsement for the idea that coding agents, used skillfully by experienced developers, can further amplify their expertise.
Thanks for the write up. Always interesting to see how very senior developers interact with AI these days.
@antirez: Introducing a regex feature that late into the project for a seemingly unrelated feature feels a bit weird? Can you explain more your rationale on that? thanks!
Once I realized arrays were a great fit for text files, many use cases I could conceive were always limited by the fact we need to grep on files. So I thought: what is the AROP equivalent for files? ARGREP. Then I made sure to add both fast, exact and regexp matching so that depending on the use case the best tool could be used. I then discovered that for many OR-ed strings regexps could be the faster way if we'll optimized. And then I specialized TRE a bit.
I vibe coded up an interactive playground against a WebAssembly build of the new array features: https://tools.simonwillison.net/redis-array
Closely matches my own experiences with current SOTA AI. Extremely useful collaborator, far from being a replacement for human intelligence and creativity.
I like to say, AI is the duck programming duck I always wanted
LLMs are the insensitive Asmovian robots I’ve always wanted, who translate and do the hardest part of my job: ensuring my emails are polite and none of my true thoughts or feelings are revealed…
Now I just need a way to protect my chats from any potential discovery, and <pew pew> business’ll be easy.
I occasionally type into slack "Future lawyers, the previous conversation is a joke. No one is doing cocaine to get through writing requirements docs."
We have a “don’t get the slack subpoenaed” emoji that gets frequent use. Incidentally, a lawyer doing discovery in the future could just search for uses of that emoji to find what they’re looking for.
There are projects that I develop mostly not looking at the code, but owning the concepts, algorithms and ideas asking questions and giving hints, and owning especially the product. But, not for Redis, not yet at least. When in the future this will be possible, server software, the way it is developed today, will be over. I bet there will be still projects and repositories, as accumulation of features, fixes and experiences will still be worth it, but the role of programmers will be very similar to what Linus did so far for the kernel. And for certain projects I'm developing, like the DeepSeek v4 inference engine, I'l already working like that.
It feels like Redis is becoming a small database, which seems to make it more convenient to use. Could you add more examples that clarify where the boundary should be?
Well, Redis is a data structures server, and has very complicated and edgy data structures like the HyperLogLog, so I have very little doubts that a fundamental data type like the Array will fit :) Also the actual complexity added is mostly two C files that are quite commented and understandable.
Sure there are also the AOF / RDB glues, the tests, the vendored TRE library for ARGREP. But all in all it's self contained complexity with little interactions with the rest of the server.A quick note: if we focus only on that part of the implementation, skipping tests and persistence code which is not huge, 4075 lines in 4 months are an average of 33 lines per day, which is quite low.
I’m a big fan of your work, and I honestly didn’t expect to receive a reply from you. Thank you. Also, thank you for pointing out exactly where I was misunderstanding the issue. In the past, I used Redis for temperature measurements in a smart farm project. I used Hashes back then, but it seems like Array would fit that use case much better.
This looks like a very useful feature. Thank you again for the reply.
I appreciate your kind reply as well :)
On safari mobile it's a page with the title header and a footer. Theres no content rendering.
Checking, thanks. EDIT: works very well on my iPhone, so without being able to reproduce is not easy to fix.
Same here, I need to turn off content blockers for the article content to load.
I should probably remove the Adsense JS which I don't use anyway...
[dead]
Is this an apologia since the PR is +22,212 -34?
Haha, ~5000 LOC with comments. The rest is tests + TRE code + TRE tests.
Is it possible to see the specification file you created and used for AI assisted development?
Very cool anyway! Can I expect a youtube video about this soon?
Yep I will release it, it is a bit out of sync at this point, but will do a pass of updating and will release it.
Got few questions:
- the project essentially spans almost 3 different (albeit minor) generations of LLMs. Have you noticed major differences in their personas, behavior, output for that specific use case?
- when using AI for feedback, have you ever considered giving it different "personalities"? I have few skills that role play as very different reviewers with their own different (by design conflicting) personalities. I found this to improve the output, but also to be extremely tiring and to often have high noise ratio.
- when did you, if ever, felt that AI was slowing you down massively compared to just doing it yourself (e.g. some specific bug or performance or design fix)? Are there recurring patterns?
- conversely, how often did AI had moments where it genuinely gave you feedback or ideas that would've not come to you?
- last: do you have specific prompts, skills, setups, etc to work on specific repositories?
[dead]
AI is a fantastic co-pilot, but you still need to know how to fly the plane when the edge cases start hitting the fan.