aleksiy123's comments

On: Newgrounds.com – A community of games, music, and art

[aleksiy123]

What a flood of nostalgia.

I wonder if AI could help in reviving these.

With my zero knowledge of flash is it possible to somehow bridge it into modern browsers using web assembly or something?

[robrtsql → aleksiy123]

Not AI, but Flash games have been 'saved' already, if you've still got the .swf:

https://ruffle.rs/

On: MicroLLM Lab – Try 7 tiny LLM's in the browser

[aleksiy123]

To be fair this is worse.

It’s verbose with a layer of looking legit play first glance sloppy UI.

I don’t mind vibe code ui but at least some ui efffort would be nice. Not just 1 shot.

[api → aleksiy123]

I think your memory of pre-AI UIs is rosy. This is a little below average.

On: Using LLMs to trace alchemical knowledge and decode 17th century letters

[aleksiy123]

I also have been doing this every round of models releasing.

Thanks for reminding me to try this new round of models.

I wonder if there are some good tools/apis that can help here.

A lot of information is often login gated

On: Claude's Load-Bearing Seams

[aleksiy123]

Woosh?

[rvz → aleksiy123]

Exactly, it is a joke of a post.

So why here?

[pxndx → rvz]

It's parody.

On: Show HN: SQLBraid – Write SQL directly in TypeScript without a query-builder DSL

[aleksiy123]

As a sidenote from the slop language, which is awful.

Feel like latest models have really got hung up on “facts” and “evidence” in a really unnatural way.

And especially Claude seems to have a lot of trouble separating it’s internal thoughts, from prompts/instructions, to output.

So you get all of these weird comments and artifacts in the output.

“neighboring versions do not inherit certification. No tag, npm publication, Pages deployment, or release authorization is implied.”

[Clickin → aleksiy123]

Fair point. I didn’t edit AI generated docs carefully enough. That release-authorization paragraph has no business being in a README. I'll re-write README from scratch using my own words. Because my first language is korean not english, please consider the editing will take time.

On: AI-generated posters don’t have to be horrible

[aleksiy123]

Tyty I was thinking about something similar

On: LLM Classification Is Feature Engineering

[aleksiy123]

You can also get LLM to optimize rules for a rules engine iteratively against some dataset.

It’s sort of like memoizing or distilling the knowledge. Works really well for certain type of problems.

On: Show HN: Real-time AI news aggregator with daily digest

[aleksiy123]

The font, the colour, and the dot on the tags all scream Claude slop ui.

[matthew_payne → aleksiy123]

Agreed. Otherwise I like the idea. I’m not an engineer I’m on the sales side of things where I am at, so I am curious and this may be a stupid question but how do you fact check?

[michelmi → matthew_payne]

I think the misinformation issue here is not as big as it may be in political related news. Nonetheless, I carefully chose only sources such as official blogs from companies (OpenAI, Google, Anthropic, NVIDIA, etc), tweets from recognized AI figures, or some of the most well known tech newspapers. There's no specific fact-check feature though.

[michelmi → aleksiy123]

I'm guilty! My background is backend engineer so I relied on claude design for UI decisions. I'll definitely do a review with this in mind.

[gneuron → michelmi]

maybe just strip the UI down to basics (techmeme + hacker news are mostly all about the text content)

On: Sony makes bold claim about game ownership

[aleksiy123]

PlayStation store not allowing returns for games that have been downloaded is the most bs policy.

In a world where steam allows instant returns with under 2 hours play time.

I have a few games now on ps where I barely played or found out the controls were terrible and have no way to return.

On: It's OK to hardcode feature flags (2025)

[aleksiy123]

You can do much more with feature flags like ab testing/experiments, integrations with analytics.

There can be whole UIs and tooling and infrastructure to manage around them and that’s what the sass offer