Cogito, Creo, Dico, Duco. Maker of @BreakerSpaceHQ
Orion–Cygnus Spur
Joined May 2009
- Tweets10.2K
- Following175
- Followers1.1K
- Likes729
Chat checkpoints as traversable/branchable like git commit tree history?
Bonus: context compression on branching
Does any AI app have this feature -
During a conversation, ask the LLM to branch off into a new session and pass enough context to explore a different direction, while the main conversation still goes on.
I know some apps support forking, but they copy the entire session history. I’m looking for something more selective, where the LLM determines what context to carry over to the new branch instead of copying the full conversation, and then automatically starts a new session (probably a tool call?)
You love your horses? Good!
But that doesn't have to mean you have to go around setting cars on fire.
Hey @postmarketOS can you guys please look up "how to enable dark mode on MediaWiki deployment"?
"just because you've started paying, doesn't mean you're no longer the product."
😅
I pay every month for Microsoft 365 and still encounter ads in Outlook. If a customer is paying for the service, should they also be monetised through advertising?
@satyanadella @MicrosoftHelps What's Microsoft's position on this?
In 2 years time (which I'll be wrong about, it'll end up taking longer)...
if modular desktop computing still exists (hope it does),
then expect motherboard vendors to start adding on-board SXM4+ support directly, without PCIe adapter cards (which I'll be right about).
Wish there was a selection pressure for Indian Banks to offer MCP servers & support agentic workflows.
NCM will also generalize the generative AI pipeline, as the image/audio/video generations already use the iterative approach of diffusion models.
So when the most used modality also uses similar architecture, the optimizations to the architecture results in big gains across all.
Just in case you're wondering, NCM is how human brain thinks as well.
We don't think one word (token) at a time like LLMs. It's the whole nebulous thought vector gets formed, which then gets processed layer by layer, with specific details added where needed.
For your day-to-day AI/token use, where do you stand on running LLMs locally on your own hardware?
0%Already running locally
50%Mostly cloud; but curious
50%Cloud service is enough
0%Want to, but no hardware
2 votes • Final results
In bangla this little word "থুক্কু" (thukku /t̪ʰukːu/) is informally used to mean "I rescind my previous expression; please allow me to rearticulate".
I love how hyper-contextually efficient it is.
Do you know any such word which packs a punch, but doesn't translate well?
BTW, anyone else is into running local models around here (at least enough to avoid subscription dependence & lock-ins)?
Would love to share notes.
Last I used Photoshop was back in 2009, and never wanted to touch it again.
And yet, today I can't wait to try out PhotoCraft on Linux.
ICYMI: "ArtCraft Adobe Clone"
Now, by this logic, the guy who cloned Coca Cola using mass spectrometry is also pirating Coca Cola (& that's the most pro-Adobe view I have on this case).
As an anti-consumer parasite corp, they DESERVE to be ripped off & this ain't nearly enough.
AI Cloning should be illegal. And I think it might be. It feels self-evident, but we may need to wait for the courts to be sure.
This morning, I took a full Windows application from Microsoft, had AI reverse-engineer it using NSA's Ghidra into a set of atomicizable actions, then translated those actions backward into Rust logic, then compiled the Rust into a brand new application.
And it did it. In one shot. So the process is:
C Code -> Compiler -> Linker -> Exe
then
Exe -> OPS -> Rust -> Compiler -> Linker -> Exe
So you feed it an application, and it produces a Rust version of that same application with 100% of the same functionality and appearance and "none" of the original code - just the logic behind that code.
I don't consider this coding.
It's not even vibe coding.
It is piracy.
This might be a hot take, but cloning an application when the application itself is used as an input does NOT, in my mind, yield an independent work.
I'm even dubious about letting the AI base its work on the application. I specifically did NOT do so for TMOG (tmog.org) because I didn't want it just copying. So I wrote a huge spec instead (which I guess could just be copying via indirection, but I'll leave that aside for now).
This time, I chose an in-the-box Windows application as a proof of concept, but there's no reason this couldn't be applied to Photoshop.
Or heck, have the AI port Final Cut from the Mac to Windows. That's a bigger ask, of course, but we're not far from it.
And so I propose we ruthlessly distinguish any process that uses an application binary itself.
Prompt -> Code -> Binary == OK
Binary -> Prompt -> Code => Binary == Clone
