Closely matches my own experiences with current SOTA AI. Extremely useful collaborator, far from being a replacement for human intelligence and creativity.
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?
> 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.
Well that's mostly my point: LLMs are mostly useful now as "code inpainting" / "boilerplate writing" when you have a defined spec
I'm doing my work mostly the same as Antirez is doing, writing detailed spec (which is actually 80% of the hard work, even without LLMs), then where I would have written the "boring stuff" I use the LLM to "autocomplete", and then see all the mistakes (which require being a senior to see / fix), correct, and iterate
It makes the work "feel" easier because we mostly skip writing the boilerplate, but it still doesn't replace coders. And companies that think they will be able to skip training juniors (in order to later replace seniors) and still have seniors onboard are making a huge mistake
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!
> And of course you have to go read the code because I have found it that AI misses polishes
Since you mentioned using other agents, do you get mileage out of code reviews with another agent polishing the unpolished bits? My colleagues swear by it, though I personally remain skeptical about its value without a human reviewer.
Love it and used a similar approach to vibe a core banking application for a mid-tier US bank with ~$10B+ in assets. They plan to put it in to production soon. That said, I felt held back by the rest of the org. the entire time because they continue to work the old way...we could have delivered it in a fraction of time and cost.
- 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?
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!
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.
The use of C stdlib localization functions (toupper, mbrtowc, etc), makes me suspect if there will be some regex behavior differences between systems or locales.
Couldn't some of the use cases presented for this be accomplished with ZSETs? I get the performance angle, but it seems that this could have been accomplished without the new API surface by selectively optimizing ZSET storage for dense values (in the same way that Arrays selectively use sparse representations).
The RE component is interesting, but as commentary here has noted it seems orthogonal to the array data structure (i.e., usable on others as well). Does this not make more sense to accomplish with Lua scripting? Or if performance of Lua is an issue perhaps abstracting OP to be composable on top of any command that returns a range of values.
I say this with reverence for Antirez as the expert in this space, but some of this new feature set feels like the sort of solution that I tend to see arise from LLM-driven development; namely creation of new functionality instead of enhancement of existing, plus overcomplicating features when composition with others might be more effective.
Reviewing 22,000 lines of code, even from antirez, with this complex of a feature set and minimal PR description sounds like a nightmare. One starts to see why major open-source software like Postgres tends to be developed on a mailing list, with intermediate design decisions discussed by the community, separate patches for different related features, incremental review, and then a spaced release cadence.
antirez: i'm curious, with the final code, have you experimented with effectively one-shotting the final result? i wonder if we can get there with GEPA, and maybe there's something we can learn in how to elicit/prompt these models to get what we want.
or maybe the conclusion is that model providers need to clean up their training data!
Redis wants to get in on the vector database market that is popular in AI. That is all there is to it.
That is the reason why the Redis author keeps boosting AI. To the point where he even uses Redis to demonstrate how many bugs AI has found. Not every software is as buggy as Redis.
It is all an advertisement by someone extremely adept at manipulating techies.
39 comments
[ 2.3 ms ] story [ 58.3 ms ] threadVery cool anyway! Can I expect a youtube video about this soon?
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.
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.
He's not, but his work is obviously not average.
Average dev work is plumbing and CRUDs.
I'm doing my work mostly the same as Antirez is doing, writing detailed spec (which is actually 80% of the hard work, even without LLMs), then where I would have written the "boring stuff" I use the LLM to "autocomplete", and then see all the mistakes (which require being a senior to see / fix), correct, and iterate
It makes the work "feel" easier because we mostly skip writing the boilerplate, but it still doesn't replace coders. And companies that think they will be able to skip training juniors (in order to later replace seniors) and still have seniors onboard are making a huge mistake
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.
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!
> And of course you have to go read the code because I have found it that AI misses polishes
Since you mentioned using other agents, do you get mileage out of code reviews with another agent polishing the unpolished bits? My colleagues swear by it, though I personally remain skeptical about its value without a human reviewer.
> Then I ask another AI
May be synthesis-antithesis-thesis works better in applied computer science... https://en.wikipedia.org/wiki/Dialectic#Criticisms
- 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?
@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!
The RE component is interesting, but as commentary here has noted it seems orthogonal to the array data structure (i.e., usable on others as well). Does this not make more sense to accomplish with Lua scripting? Or if performance of Lua is an issue perhaps abstracting OP to be composable on top of any command that returns a range of values.
I say this with reverence for Antirez as the expert in this space, but some of this new feature set feels like the sort of solution that I tend to see arise from LLM-driven development; namely creation of new functionality instead of enhancement of existing, plus overcomplicating features when composition with others might be more effective.
or maybe the conclusion is that model providers need to clean up their training data!
Who is going to do an LLM free fork?
That is the reason why the Redis author keeps boosting AI. To the point where he even uses Redis to demonstrate how many bugs AI has found. Not every software is as buggy as Redis.
It is all an advertisement by someone extremely adept at manipulating techies.