mpaepper

Who would be among those 5? Are these big tech? Or large corporates?

It would be fun if many shipped in some $ for this to be a realistic bounty, but then again, OP could just take the money him/herself...

Someone doubled the bitcoin amount :D

Why did you decide for the 5070 Ti? You will always suffer compared to the 5090?

There seems to be no hold out data for test, so this is just overfitting?

I switched from CC to Codex a few days ago. I get limited much less and the code quality is similar, so not looking back

Whoops, seems like my question got removed while posting, so here goes:

It seems Gemini couples app activity (I can see my chat history) with AI training.

This is horrible...

Any way around it to make Gemini usable without my data being used for training?

It says 24y in his profile - is that really the more senior at Ars?

How are the runs isolated? Can I run multiple parallel sessions on the same repo? What about security / sandboxing to avoid exfiltration of data etc? Thanks!

Yes and no I'd say. It's still the case that now only by iterating and testing things with the AI you get closer to an actually good solution. So up front big spec will also not work so well. The only exception maybe if you already have a very clear understanding and existing tests (like what they did with the Claude's building the rust c compiler to compile the Linux kernel)

Maybe, however, they might not care as the API is freely available anyways

For example this post here becomes: https://news.gcombinator.com/item?id=46780583

How much memory do you need locally? Is a rtx 3090 with 24gb enough?

You should look into the new Nvidia model: https://research.nvidia.com/labs/adlr/personaplex/

It has dual channel input / output and a very permissible license

Free generator for e-invoices here: https://www.e-rechnung-online-erstellen.de/kostenlos/e-rechn...

You mentioned needing 40k tiles and renting a H100 for 3$/hour at 200tiles/hour, so am I right to assume that you spend 200*3=600$ for running the inference? That also means letting it run 25 nights a 8 hours or so?

Cool project!

Hi everyone, inspired by Alex' cool article about ASCII rendering (https://alexharri.com/blog/ascii-rendering), I revamped my hero section. It now consists of a matrix style rain of characters which transitions into a pseudo random ASCII rendering of an image of myself.

Seems like the merging with Replit didn't work so well :p

He might already have enough money, so doesn't care if he gets the absolute best resources.

What about the security aspects, can it run anything?

This seems awesome, will try.

Unfortunate naming given I named my repo which does open source locally running speech to text vibevoice 7 months ago:

https://github.com/mpaepper/vibevoice

That's why we all code with voice now, because it's faster, right? Right?

Yeah, Cloudflare is a good idea, that should probably help block them before even getting to the site.

I've just added it :D

But I would guess that there will be new domains that I don't have in my blocklist and then I need to add them again and I would like to have this as a crowdsourced effort.

I mean I run a SaaS and get many fake registered users / bots.

What I did for now is:

- Added a honeypot field (invisible to users, but bots might fill it) -> if it's filled, instant reject - Added a check for spammy domains -> if it's from such a domain, instant reject

Are languages other than English also supported? Or is this for English only?

Nope... It IS using a vector database / faiss embedings for the semantic search.

Check the indexer: https://github.com/Olow304/memvid/blob/main/memvid/index.py

Moin Tom,

Thanks for putting up with the work - let's go!