ink-splatters

This is a usual crap Apple has turned to, other things are so fucked up, so I’d close my eyes on the former. E.g.:

Apple (iCloud) Data Recovery works only if you deleted files from Drive via GUI, which places them in Trash.

So you actually do have them. Whaat? Why would you need a recovery? Good question.

Now it gets really interesting: you’ve emptied the Trash and now wanna to recover some.

But they are no more. Gone. Can’t be recovered anymore.

And there is a reason of course: because fuck you, that’s why.

And it’s documented FYI, so it’s a feature.

Checkmate.

It cannot write some kind of short texts either.

The experiment was: given existing Experience section of Senior Software Engineer CV (manually and carefully written), write 2-4 lines of high pitch About [me].

gpt-sol-xhigh just could not do it, making a complete AI slop mess.

It became substantially better when I asked to get a sample of real Senior/Principal engineers CVs, that it would be able to connect with meaningful online presence/contributions of their authors, and draw ideas from that.

Nevertheless, the remaining issues were critical, with their classes spanning:

- word for word repetition;

- tautology (phrases mapping to the same semantic entity);

- category mistakes (combining apples with oranges);

- faulty composition of generalised and concrete terms.

Before throwing it away I decided to give it a try and asked for strict prompt following, setting low logical errors threshold, and eventually providing a formal proof that it complied.

It took spaCy, doing NER and dependency parsing; then I suggested adding stanza for constituency parsing.

After slapping together the artefacts of analysis and thinking a bit, it produced great phrase (to my taste).

-

Then when I asked to apply the framework and improve bullet points in some experience block, it did 2 of 4 well, then miserably broke down; I’m not sure if it’s harness issue (codex) or fundamental model restriction.

-

So no, without substantial investment in steering, SOTA AI doesn’t perform even remotely close to a human, in complex reasoning.

Having single binary output is completely different problem and is solved for both Python and typescript (bun supports the later).

You can tune java runtime in many ways, achieving impressive throughput/latency for your type of workload.

Next to none of them will get you nearly as good cold start times as of native app, if using free java.

There was GraalVM and its ecosystem which included Java Native Image - first thing I’d evaluate if thought about non-server side, performant Java application.

But it all had been sadly swept away by Oracle from free tier.