I do not feel good about this. I really want SQLite (and the Turso re-write of it) to win for tiny apps that people will build more and more with LLMs. Desktop or server. Even serverless.
The core tech is open source so that is good. Will it stay? I guess Turso hosting was not making enough revenue?
Thanks but you do understand this makes it hard for folks to select Turso. With all good intentions parent companies kill acquisitions.
Supabase is hosted Postgres with wings. Turso seemed like it would be the same but using SQLite based approach.
So either Supabase now uses the Turso sync + Postgres or something that needs Turso or abandons it. Not sure and I am not asking, just sharing my thoughts.
No, I truly don't understand that.
It is true that some acquisitions fail, but most of the ones you see failing are doomed from the start and are a way for the founder to exit, acquhire, etc.
I had a never-ending host of options at my hand. Turso grew revenue > 5x this year. I had no reason to accept an offer that wouldn't have a great chance of success.
SQLite/Turso fits my own agent/harness mental model very well but I am, as folks in the valley would say, a bit of an anti-capitalist.
I am working on my own agents that are anti-tokenmaxxers. SQLite/Turso is part of the deployed app architecture from my harness. Thanks a lot for taking the time.
Did you check out the post? Supabase sees Turso as the answer to workloads not well-suited for Postgres. This seems like a decent Yes, And proposition.
yup — we see Turso/SQLite as complementary to Postgres for specific use cases. The blog post doesn't mention it yet, but this will power our smallest instance — "Spark" https://x.com/saltcod/status/2106078176464036044
I also have my own doubts about this acquisition, but as I explore sqlite-per-user models I'm also seeing benefits to having some central control plane. I thought they would've made a natural fit on Cloudflare.
I am fully onboard with LLM generated code if that is what you mean. I literally get client work titled "Need Claude led Engineer". SQLite is a great option for the LLM enabled future.
> The core tech is open source so that is good. Will it stay? I guess Turso hosting was not making enough revenue?
You just answered your own question. Why would anyone pay for Turso if the core of the software is available for free and being licenced permissively under MIT?
Because they don't want to self-host/manage it. It looks like this is an acquisition, not an acquihire, so it's unclear whether or not Turso was making enough to sustain itself or not. There are plenty of companies out there who release open source software and make money off of hosted/managed offerings of it.
Liability. Compliance. Chain-of-responsibility. Risk. This has always been the case in business, and it will continue to be the case (at least until artificial intelligence actually replaces that need).
I have been programming for about 30 years (including school years). Professionally for 18 years.
Can anyone tell me why we have 40 or more programming languages, with about 10 popular ones? Then about 20 frameworks in each of them. And add another 200 popular libraries for each language? This matrix make no sense till you realize - it is preferences all the way down.
Most of us engineers have built our own mental model of programming. We are all right. But the users do not care. LLMs are here to produce code closer and closer to the metal as needed. They can sit and create a graph out of every spec, use an AST that they develop and run on the CPU if they have to. They will do it. No amount of us discussing will stop that.
Programming is going to be re-invented. I do not think the current ways to write software will even matter.
Your comment started strong. "30 years programming experience", asking interesting questions, I really hoped you'd say something profound... then it went down to whatever this is. The reason there are many programming languages and frameworks isn't programmer's preferences but rather their utility in solving specific problems. Take Prolog for example. Can you technically do what it does in JS? Yes. Can you do frontend in Prolog? Probably yes, but you wouldn’t [ab]use one tool when the other is due.
Your argument reads as someone who claims to be a professional but opens the toolbox and says: "do you know why there are so many tools?" And then goes to answer: "because I like it so"! What the ... ?
If a language is Turing complete, why build another language right on top? Most of the interpreted languages are running an engine written in C. Was C not enough? Or was it that we needed abstraction?
It is nice to be in our bubble but if what you said is true, why do we only have like 3 major instruction sets? Why not 40? Programming languages are just easy to create - this is a good thing and we created too many. But it absolutely fractured the industry.
Look at the average job post. There are requirements for system design - good. Algorightms - good. Then it goes into this whole language/framework land. Remembering syntax is literally there in many companies interview. These are preferences. If we understand how a computer executes binary/assembly, the layers above are not as relevant as we have made them.
Yes, we need abstraction. X being written in Y doesn't mean you can build the same systems, with the same adaptability, reliability, and performance, within the same time and cost.
Obviously there are also unnecessary differences between tools, and hiring shouldn't focus on easily transferred skills
I have personally wanted to learn and actually use Lisp. I will get to it, even with all the LLM enabled programming. But yes, this is one of those things.
We have reinvented so many ideas many different ways in many different languages and frameworks simply because we want our flavored version.
What I mean is that a lot of the popular languages have an engine written in C. Fairly common pattern. I get it that we want to abstract but sometimes it feels we just want to avoid dealing with a language that is one layer below.
I agree with what you said, and _sometimes_ it's true, but I still wouldn't call it a "preference". One could argue there isn't a "need" to deliver faster and come up with solutions to problems, but is it a "preference"?
Maybe I'm completely off base here, arguing about semantics.
You can go quite far using a human language to Bash grammar based setup but at some point the input prompts are harder to translate. The OP has existing projects that work with AST quite deeply so I assume they know about that already.
I am building a natural language to CSV/Excel commands for a "wrangler" type desktop app. Same issues. The MVP is being built with parsers of sorts, entirely code generated. Then I want to fine-tune a tiny model at some point.
I have been trying a mix of fine-tuning and I am amazed that most people do not see this coming.
A tiny, smaller than 1b parameter model, fine-tuned, can kick ass for constrained work. I do not have a lot of budget, I fine-tune only on a 16GB M4 Mac Mini. But that also tells me the potential is wild. Progress has been slow since I moonlight on this.
I have been trying to build a set of models + agents for full-stack development, where each model does only a small piece, like take user prompt and break into backend/frontend tasks. Then a Rust+Diesel model, a Rust+Auxum model, a Solid+Router model and so on. I know this is wild but this is just theory - can 5 or 6 Qwen 3.5 0.8b models do full-stack web development? My hunch says they can, better than what most people expect. Heck, with a good harness, it might beat all the cheaper models for the specific task, like Haiku or Luna.
I think a sub-set of people see this coming, I also think it isn’t just fine tuning open weight LLM models. A few people I know who are thinking along the same lines with architectures like BERT etc.
That being said it’s much easier at the moment to continue to use the frontier providers for most general tasks, that is the argument I’ve heard.
For creating these types of fine tuned local models, on constrained hardware for inference, I do think this is the way to go for specific tasks too!
The issue I find with this is that the frontier models still outperform the small finetuned model on its specific task. So much so that the ROI on doing fine tunes is likely negative. I would love to hear some specific example where it did provide value though, if any has any. That would be helpful to start being able to find similar cases.
There are lots of distilled models on huggingface that are much smaller than, say, Opus. They are distilled from Opus or Fable and show clear improvements. I do not have the budget to fine-tune a 30b or more parameter model but from my tiny model experiments, the results are quite clear. Again, I have only a couple small tests.
Have you actually fine-tuned yourself? Email categorization comes to mind and there are tons of non-LLM approaches even that will give fantastic results. How did spam filters work before LLM?
I think LLMs just made us think that is the only way. It is not.
Maybe we're getting into a world where our general models can make their own separate fine-tuned models as utilities just like they would a bash/python script. If making a fine-tune is cheap and fast then it can also be throw-away and constantly improved.
I think LLMs may actually help us get to CLI/API driven development. At least, that has been my experience.
Even though most of my projects have a UI, I build a CLI/API version so that the LLM can interact with it directly. I have been using this "CLI driven development" approach for more than a year now and have had fantastic results. The CLI arguments make it easy for LLM to interact with software it wrote.
I usually ask LLM to build a lib, then expose as a CLI and a RESTful API.
As a developer/user I hope for that outcome too — if everybody is using your app through an agent you might as well cut the maintenance cost and drop the GUI, or at least have a nice API alongside it to make it nicer for the agent. But I wonder what it does to the financial incentives to produce software.
I came across this recently. I was scanning for tiny models from HF using their search API. The script was generated by an agent. When I ran it, Qwen 3.5 did not make it at the top. Turns out, models generally prefer older content (training) but that the scanner also did not give any importance to recency.
I was learning Rust slowly when the LLM enabled coding became good enough. I switched from learning to full on building with Rust. I still learn high level concepts as needed but I will not be able to write Rust on my own at all.
And that sounds scary but the way I got over the fear is by realizing there are many things that I do very well but I do not know their internals very well. Driving is an example. I barely understand what the steering wheel, clutch or brake pedals do. I have driven over 130,000 Kms and I will perhaps drive more than double that in the next many years.
I have been building software since PHP/Drupal days. Got into AWS S3 as a beta user. Adopted Memcached (and MQ) in 2008 out of necessity. Then Python/Django for 10 years. Then Rust. And tons of JS/TS. I owe a lot to my curiosity. I believe we can keep learning what we need and still delegate most of programming to agents.
There are two types of programmers: the pragmatists who see programming as a chore and would gladly never write a line of code again given the right tools, and the gardeners who don't want their enjoyable and rewarding garden-tending work taken away from them.
The "pragmatists" who get excited developing a prototype for a week before they realize they will never be able to ship something anyone else will use because each trivial change becomes exponentially more difficult for the LLM to implement and completely impossible for the "pragmatist" to reason about, with every new commit liable to break something else.
Still waiting for this revolution of amazing 10x software! It's been 10 months since Everything Changed in November, surely the 10x pragmatists could have leveraged their effective 8 years of development time? Or maybe we'll move the goalposts again and say that actually, Everything Changed with Astra, we'll just need to wait another three months?
I am not an expert in this domain but as an engineer-turned-researcher, this looks a lot like GliNER with a fitting harness.
This is something I focus on in a bunch of my experiments - how to get immense value out of tiny models (<1b params). There are lots of different architectures out there and there is so much to optimize if you know what you are asking and have a grammar to constrain with.
Great to see this and I hope this is a lot on top of what is already openly available.
More and more such experiments. I felt sad for a couple months when I realized that writing code will not be the same since. Now I am on the other side.
LLMs are interesting in their own ways but as an engineer, this is a way to unlock a new way of building software.
I recently build a Claude-assisted Excel/CSV parser for a US based property management system (tax compliance). Uses Haiku and has a lot of deterministic code to extract column/row combinations to check known formats and finally handing out the headers to Haiku to give us a translation plan to our support columns.
These would eventually become part of the software, in a tiny LLM. The gap between training (such tiny LLMs) and inference will shrink. We can consult Claude for edge cases, create sample dataset and train a the tiny LLM on demand so we go to Claude less.
The tooling that a project needs is really important. Something I have been feeling as well. Not just in LLM building projects, but regular software projects that are LLM generated.
I think I am on your arc as well. My learning on different topics is growing every day, but there’s a limit to how much I can absorb. With the LLMs the experiments stay just beyond that horizon and I keep chasing.
Stated too strongly, but I think this could be the model for education (some subjects anyway). Everything personalized to your learning goals, grounded in experiments that give a tight feedback loop and with a model that never gets tired of re-explaining something for the 10th time.
Yes they are great for learning at own pace, trying out new things.
I have accepted two things that make me a happy engineer now: AGI is not here no matter what they say and LLMs are still very useful if one knows how to use them.
They are another layer of abstraction and like you said they do not tire. There is a lot of optimization needed so we can reduce wastage (running 1T+ LLMs for most work is wastage).
Haha, I thought about this today. I'm traveling and walked through a university campus. The new students are coming in and I thought wow, wouldn't it be wild to be a fresh in student in the age of AI (it's been a long time since I was college). But, then I thought, actually this could be an incredible time to be a student. If your curious and motivated the agents can be amazing partners. I think the students who crack how to use AI now are going to be the ones who really run the table as this economic wave crests. But, yeah, you're right on with the Wall-E comment. I would guess many (most?) will turn their brain off and then what's the point of even being there?
When we hyper focus on finding something, we find it all the time.
The world of tiny LLMs is so interesting. It is unlocking novel ways to encode information. Why focus on the style of writing instead of the subject matter?
The core tech is open source so that is good. Will it stay? I guess Turso hosting was not making enough revenue?
reply