diegoperini

قبل شهرينdiscuss

I have the opposite experience where Gemini (even the flash models) has the only useful model for my reverse engineering related use case. My hunch is Google utilizes its free access to entire Google search indices to train itself from niche non-English speaking community websites, much frequently and in a "relevant" manner, which in the end gives these models the most up to date info for this particular kind of work. Every other model is just either 10 years outdated with their answers or simply hallucinates like waaaay crazy.

diegoperini

قبل 3 أشهرdiscuss

If I am not mistaken, it's even shown in the marketing materials to build suspense.

diegoperini

قبل 3 أشهرdiscuss

> Water blobs vs. fireballs. Pretty sure there's a nice videogame idea hiding in there somewhere.

I like the way you think. :)

diegoperini

قبل 9 أشهرdiscuss

That analogy may not be suitable for this case because value proposition between the aesthetics vs the function is different for visual art projects compared to software. There is also the maintainability factor where most aged software (especially the closed source ones in private sector) change maintainers every few years. Old maintainers most often lose access to the source code and become unreachable after leaving their job.

diegoperini

قبل 9 أشهرdiscuss

"Protection against malicious use" isn't as cool as "model welfare". I'm renaming my authentication function to "examineCrest()".

diegoperini

قبل 9 أشهرdiscuss

I recommend replacing "hi chat" in the test spell with "Mortal plane, I greet thee".

diegoperini

قبل 9 أشهرdiscuss

> I'm not quite sure why you'd want to run Erlang on it, but the hardware exists.

Erlang is invented before IoT was a thing to facilitate distributed computing for telecommunication in a highly reliable manner. It makes perfect sense to adapt it for driving fleets of cheap IoT devices.

diegoperini

قبل 9 أشهرdiscuss

> And here are my clearly unimpressed “friends” >:(

These friends don't get it!

diegoperini

قبل 10 أشهرdiscuss

Low resource footprint, written in Go, embed-able in any Go project as a library, compiles to mobile with little to no modification, supports config change without restart, has plugin API.

These were the reasons why we used it in my previous job.

diegoperini

قبل 10 أشهرdiscuss

> it has a truckload of data

It would be "artificial" only if LLMs performed badly despite having an equal amount of data containing examples of eastern customs in its training set. Even that's arguable since we don't (didn't) have the benchmarks for this particular case before.

diegoperini

قبل 10 أشهرdiscuss

It's no different than GPT answering a prompt with "That's a wonderful idea!", except it's in a different language than English. It's a good thing if LLMs can do this in every language and for any culture with no compromise.

diegoperini

قبل 6 سنواتdiscuss

As if this is not enough, star count in the repo is currently 666! Coincidence?

diegoperini

قبل 10 سنواتdiscuss

Same here. HN is addictive, but also insanely useful in some cases which makes it hard to leave like any other mentioned site there.

I literally owe many of my succesful professional decisions to researches that initally started here. I find some interesting article, read the comments first, then the article, then the comments again. In the middle of this flow, I decide whether it is worthy to save to my Pocket account. Those things in my Pocket quite often become kickstarters for things that I eventually adopt using or learning. I see no way of giving up such opportunity. Why would anyone do that? (That is a serious question that I really wish there exists a convincing answer)