never_inline
1. They may be trained, in theory, to inject subtle back-doors into certain kinds of generated code.
2. They may be also trained to include back-doors when deployed in public-facing services where user can provide text or image input.
3. Chained with (2) they may be also trained to exploit their inference environments, which though a big feat, not outside the capability of nation-state hackers.
It would help to clarify these things in the post. Your software is atypical of common Go software in the wild. The purpose of Go -> Rust rewrite would be usually the efficiency of rust.
* How many lines was the result? Considering how much err != nil and line splitting needs to be done in Go, did you at least reach 30k SLoC?
* How was sloc counted here? includes comments, blank lines or not? (something like cloc will give a good answer).
* Performance characteristics of resulting rust, was there an improvement? It maybe appealing to say Rust is Always faster than Go.
As usual these AI coding posts tend to be loose on actual measurements. Don't like it. Granted you can't do too much experimentation with prompting techniques since you're paying per token. But at least you can assess the code that was produced?I am in a similar situation - I have a hobby web tool hosted on AWS lambda's free tier behind cloudfront which is quite economical (I usually stay below limit).
But over last 2 months I am getting many thousand requests a day. In theory there aren't many crawlable pages in my site but these bots are hammering the search endpoints with arbitrary queries which are somewhat related to the subject matter (must be powered by some weak LMs because they're not valid queries, just generated in a plausible way).
I have seen quite a few websites put behind anubis or some other sort of verification system in last 6 months or around. This satire from Krazam [1] was on point.
[1]: https://m.youtube.com/watch?v=IU4ByUbDKNc&pp=0gcJCYsCo7VqN5t...
This pretense that the entire value of source code is the "spec" / "requirement" is alarming.
The value of the code is how well-formed the spec is + how well tested it is in the real world. So prompt / mockup cannot replace code.
You might assume we are able to detect all malicious behavior at runtime. But "stuxnet" and more recently, the xz compromise say otherwise. What if a not-so-popular crate deep in the dependency chain subtly introduced a LPE in it's code?
I don't question your credentials but I also think many things deemed to be IIr innovations may not even be. IIr came through CW -> Sintashta after all and BMAC influences are overstated. For instance, Soma may have a root in this region, but the myth associated with theft of divine intoxicating drink and it's function as the mead of poetry must predate the specific IIr Soma cult.
Without going into depth of that, here's something actually more inspiring (actual excerpt from Rig Veda).
tvā́m ugrám ávase carṣaṇīsáhaṃ rā́jan devéṣu hūmahe
víśvā sú no vithurā́ pibdanā́ vaso amítrān suṣáhān kr̥dhi
> We call for help, the fierce, ruler of clans of men, king of Gods (Indra)> All of us that is weak, strengthen it. Make the enemies easy to subdue
(The acute accent is an udatta - high pitch, vedic is a pitch accented language. I would expect IAST with accents, not whatever randomly capitalised things it threw at me).
If we are speaking of the classical times: yes, India was on-par with the greco-roman and chinese world; left a cultural imprint on east and south-east asia and traded with the western world too. But the rise of pacifist religions, being in a nice position to be attacked from central asia, and internal strifes basically rendered it useless in the last millenium. Huge population, uncontrolled urbanization and a corrupt education system is the bane of this century. If we don't solve that, no amount of classical civilization is going to help. Germanic people were considered primitive by the greeks and romans, now look where they are!
> How hard would it be to build a new Google Search with a small team and an LLM?
> How hard would it be to engineer a new Google Drive and Docs suite?
> How hard would it be to create a new phone operating system?
And who has seen success with that? It's all theory now.
> LLMs may actually drag our super-valuable tech industry back down to earth and commoditize everything we've ever built.
Because most of the tech that has been built was not super valuable at all. Linux, GCC, docker maybe. But your average SaaS was always a commodity.
Here's a paper by a non native English speaker. The lack of the formal style doesn't cause any issue. Preciseness is what matters.