smusamashah

This reminds of another awesome actually ASCII animation library https://play.ertdfgcvb.xyz/

Some of these look very interesting. Training diffusion algo, emergence algos, hashing etc etc.

Each demo includes a prompt as well. Source: https://x.com/mhmazur/status/2107459343218057324

If it looks like that you, you will be seeing it everywhere.

Also 3 days ago

> I have very little need to run Agents over night, as my throughput is limited by my approval.

> I really have no idea what to do with my agents over night.

Mainly the improved quality of images look most interesting to me.

Hi, Could this have been a KOReader plugin too where all this processing etc is done on KOReader/Kindle itself instead of another machine?

I had no idea that we there are SO many aesteroids that we keeping track of. How are we even doing that? How do we recognize one aesteroid from another?

A DIY explainer with photos https://www.metabunk.org/threads/the-moon-tilt-terminator-il...

AI does not make good pixel art yet.

I was at uni in 2005. A mate wanted to search for a book and wrote something like this in Google search "go to digital library and find me this book". We laughed at what he did back then, searched for "<book name>" in quotes and may be with filetype I dont remember and found the book.

I think about that lots of times when I google these days. That he wasn't wrong, was just asking it 15 years too early.

> our system allows a Unitree G1 guided by GPT Astra to clean up across the room and retrieve a remembered object from an underspecified request

This is not "on its own".

Can you please explain what does it mean by bitter lesson in this context specifically? I keep seeing this term here. I know there is an article of the same title but I still don't understand.

Yup and I think these examples demonstrate just that. From my experience, both Claude and ChatGPT iterate over what they can see to build things like these. I don't think these examples are made without vision.

I think Opus 5.5 is at same level now. I have seen too many videos made by Opus 5.5 today on twitter.

https://x.com/victormustar/status/2102707412704919910 horse galloping pixel art

https://x.com/LexnLin/status/2102133072585965759 moving train pixel art animation

https://x.com/jkeatn/status/2102441348075057539 painting with code

https://x.com/LCSlates/status/2102503027340988559 video, very detailed prompt though

https://x.com/aj_dev_smith/status/2102504509637587339 generated song/music with code

https://x.com/aj_dev_smith/status/2102575577563570450 another song

Repo should have at least a few screenshots

The A becomes An for the same reason as the linking R https://en.wikipedia.org/wiki/Linking_and_intrusive_R

As a non-native now living in UK I noticed this R sound in some accents. Someone said 'Java (r)Options' which when I asked they didn't even realise they were adding it. Both this R and N in an seem to be used break the continuity of vowels between words.

There is very often a certain softness to the fonts in generated images. Why is that and is there a name for it?

Thinking more, I thinking the softness is actually inconsistency. Because the letters are generated, no two letters will be exact same and if zoomed in some edge might not even be perfectly straight. Another thing we can do these days (I think author should really try out in V2) is to use code to generate the . You may have seen examples of generating Javascript based videos with Claude. Same can be done with posters. Generate a font sheet and use that in code generated poster with image generated background.

Webwormhole.io should work theoretically on file of any size because it does not keep the file being downloaded in memory/cache first. It downloads as a file as soon as it starts.

In practice, I have used syncthing to transfer many giga bytes data from one work computer to other because syncthing uses lot more discovery protocols etc to work around restrictions.

Looking at the history of the github repo of this show hn, the readme was previously linking to now Sold to LimeWire SnapDrop.net. Github author recently changed that to SnapDrop.me and is either doing a Show HN himself or this is another fishy play by LimeWire.

But SnapDrop was sold to LimeWire from what I remember, wasn't it? I have it on my (somewhat popular) list https://gist.github.com/SMUsamaShah/fd6e275e44009b72f64d0570...

Edit: so that was SnapDrop.net this is so confusing now. Are you the author of that GitHub repo?

I got rate exceeded error when pressing generate button. This guide should have use browser version (wasm etc) of GraphViz

Astra isn't doing well on bullshit Benchmark https://petergpt.github.io/bullshit-benchmark/viewer/index.n... and is even worse in Legal department.

Qwen 3.8 Max and Opus 4.8 score highest.

Tweet by the author https://x.com/carterleffen/status/2100405732935868840

So its more like a harness (like Codex etc) on top of any existing LLM?

Doesn't this mean Jev can be used to drive a car as well?

https://x.com/harshagundal/status/2100044305536889015 tweet by the author

But if you only remember facts, can someone else pretend to be that person you remember with those facts?

I think it should be doable now. Someone might have tried this already. I do know people connecting AI to TVs to cleanup all the bloat automatically and it works. Saw a few posts on twitter.

Biggest benefit of all this getting the control of hardware back to consumers. Software has been the soul of the computers which only knowledgeable enough could put into hardware for a long time.

Now (almost) anyone who owns a programmable device also controls it the way they want, as if they actually own it.

I am stretching a bit here but we are almost there now already.

I wish these models start writing super optimal code that can squeeze very last bit of the chips so that we can get rid of Electron and similar bloatware.

No. It's like the skin behind ears is pulled moving ear slightly back. Can't move tips.