If you don't know that already and "using it as such" ... your post should start with "I blew off $4k on a toy several months ago".

I wonder what parent poster means with „useful” and what he actually tried? Feels like he was just comparing some benchmarks.

Yesterday I downloaded Gemma4-26B with Ollama on quite rusty desktop with 1070 8gb and 32gb of ram and Core i5-9400.

I drop photo of my water meter and tell it to read the value and serial number. It was far from instant but it was also easily under 3 minutes and result was correct.

Earlier like in February I was trying the same photo with Gemma3 on the same hardware and results were bad.

Half is a joke half not:

Not sure how you are working but we have this novelty idea where people have daily meetings like 15 mins each day to update each other which tasks they are busy with.

We also have refinement meetings where people are involved in clarification for each task so they are not surprised by requirements.

So we do planning meetings every two weeks. Each ticket is tied to the code in commit.

So by code review time anyone doing CR has all of the information in few clicks and some of it already in their head.

Questions arise like, maybe instead of doing 4x PRs he could to 2x more code reviews and 2x more PRs still or even doing 3x more reviews. Why parent poster didn’t write anything about his involvement in reviewing the code - could he be just asshole team member ?

I am fully convinced companies actually loose money because they have bunch of employees who waste time “bending reality” thinking they need custom workflow because “they are so specialized”.

But it already is.

You can’t just buy H100 there are government limits on that.

RTX4090 maybe has no government limits but NVidia is definitely limiting bulk orders per retailer. I guess if you buy a lot from each retailer you will most likely get flagged in one way or the other.

Local model as such will give you "autocomplete on steroids" but it is not going to run away and implement cross project feature like frontier model in let's say Cursor.

So there is no value in testing quality of answers, but there is value in testing token speed.

You just have to have correct expectations.

Is autocomplete using LLMs really useful? Even with frontier models I found it to be about 50% right, I turned it of and prefer to use IntelliJ built-in, it is way more reliable.

For me local models is all about quality, and how to achieve that - e.g. by providing guardrails that test the job done.

People who believe AGI is real.

Just AI is real.

ML is real. Chatbots are real. “AI” is a marketing term that John McCarthy invented because he wanted more money for a summer study at Dartmouth—direct quote from him.

Ugh, let's take a step back and make a distinction:

I don't need your fluff. No one cares how you arrived writing another crud line to save an object to database or sent yet another AJAX call.

If you wrote some genuine great compression algorithm that's a different take on compression, I would like to see step by step reasoning and eventual dead ends.

I shared my thoughts in the context of someone saying that one should be able to share your line of thinking when asked to. Whether "when one asked to" applies to keystroke by keystroke blockhained versioning isn't my point of discussion.

I get it, that the overall discussion is about DeltaDB. I'd say interesting concept to toy with. I'd pay more attention to "micro commits" as the idea more than the keylogger.

why this particular object though?

why didn't you add these three other parameters to it?

how does this default value make sense when unset?

mostly things that end up not-in-the-commit that 3 years from now people are gonna wonder about is really handy to know

I strongly doubt that.

I think a good argument ad absurdum for this is to look at how some recipe sites give the entire genealogical history of the author and an anecdote about how their gammy met Theodore Roosevelt and he stole her pen. Three pages later I discover I need to go to the grocery store because the recipe requires sour cream. And the store is closed so I need a different recipe.

Don't fucking do that. Do something way less than halfway to that line.

Agree on the software case. Disagree about the recipes.

Food writing is its own genre where the recipe is one part of a larger story. Can often include travel stories as well.

Maybe not your thing. But definitely has its place.

Can we agree that this flavor of recipe writing should not be applied to software? That's the point I was going for (hence the ad absurdum header)

The web is probably the closest thing the software industry has to a truly universal, open application platform. There is corporate influence, but it is substantially more vendor-neutral than any other UI platforms.

The web stuff mostly uses licenses such as MIT, Apache 2.0, and BSD. GPL-licensed projects exist, but still many more on permissive side.

Web is based on open standards developed through organizations and specifications are publicly available, royalty-free, and implemented by multiple independent browser engines rather than being owned by a single corporation.