how hard could it be?
Austria
Joined February 2007
- Tweets5.1K
- Following7.5K
- Followers1.1K
- Likes175K
Christian Langreiter retweeted
The future of software
In the limit, of course, software won't mean anything anymore. Everything digital will be instantly created at will. But in the interim period we'll wander through an increasingly odd in-between age for software. This transition periodwill be defined by three new precepts.
Everflux software - instead of stepping from release to release, months apart, software now evolves continuously.
Software creation has broken the sound barrier of our own keystrokes, and every model release pushes it faster. There is no reason to wait weeks or months for the next release when a single company merges over 30,000 code changes a day. Cyber capabilities are also progressing at an increasing pace. Bug and vulnerability fixes need to ship quickly and continuously. And every piece of software sits in a lattice of dependencies, each one now shipping at a blistering pace. Software will have to move accordingly fast just to keep from breaking as everything around it shifts.
Translucent sources – A new territory has opened between open source and closed source.
Today Claude will happily pick apart any Electron app, and any binary shipped with debug symbols has become a reverse-engineering playground for LLMs. In other words, much so-called closed-source software is now open source in all but name, and keeping code closed makes less and less sense.
Even the notion of IP and copyright is breaking in software: Apps don't even need to be accessed to be reproduced. I'm writing this text on a personal text editor I prompted Claude to vibe-code from a few videos of people demoing editor features they liked. A mere description of the interface is increasingly enough for an LLM to rebuild the internals, whether or not they resemble the original. Software IP seems to be dissolving like cotton candy in a raccoon's paws.
Bespoke features - Now that all software is open source, nothing prevents us from modifying everything.
And personalization is just one prompt and a couple million tokens away, so there is absolutely no reason anymore to wait for someone else to add this feature you want. Everyone becomes their own product manager. Want a search box, an API bridge, a custom button? It's a couple of minutes away, mostly executed in the background of your daily life. Soon we'll want to personalize everything.
A major challenge appears when bespoke features crash into our first tenet: everflux software. How do you customize software without cutting yourself off from upstream? I could fork it for good to add my search box, but I'd lose all future benefit from the software creator, be it new security updates or other updates to the rest of the software. How do you personalize software that was never meant to be personalized, without shouldering all of its future maintenance?
Merge conflicts won't be the exception anymore; they'll be a constant of everflux software. Agents will rebase our personal features onto each new release overnight, and software will look less like a product and more like a living species, evolving through constant mutation.
Image: M.C. Escher, Metamorphosis II, November 1939 - March 1940
Christian Langreiter retweeted
good read on why humans, like llms, get a lot more powerful when given a scratchpad.
[new blog post]
Writing as a thinking tool
muratbuffalo.blogspot.com/20…
Christian Langreiter retweeted
i pulled my kindle, podcast, youtube history to re-affirm what i think is interesting to me
then quickly spun up this book timeline
Christian Langreiter retweeted
The models are very good at creating custom spaced repetition apps with algorithms adapted to you and the problem domain ("review my learning and improve the efficiency of your scheduler") plus tailored explanations for anything that you consistently get wrong.
Christian Langreiter retweeted
A few months ago Surya (@kickingkeys), a designer at Websim (@websim_ai) in New York, posted a project that went viral: “You can just RL a coding model to paint with javascript btw.”
We sat down with Surya and were shocked to learn that he only wrote his first line of code in 2024 and had not heard of RL before January. We wanted to know how someone with that background goes from zero to training models in under two years, and whether anyone else could do that too.
Our top 2 lessons from Surya:
- Anyone can learn how these systems work if you are curious and willing to put in the time.
- The best way to learn is to spend less time asking what AI can do to serve you and more time asking what it can do to serve the people around you.
Some of Surya’s recent projects include training models to paint, setting up AI for a coffee shop owner so he has more time to write, and having agents watch him in the art studio and turn the footage into a reality-TV-style story.
Surya is doing this for the love of the game.
Read our full interview in the thread!
cc @thisisrayouf
Christian Langreiter retweeted
Just a reminder that DeepSeek V4.1 Flash 1017, GLM 5.3 Flash, Qwen 3.8 Next Flash, and even Qwen 3.8 27B are all outperforming (in both intelligence and capabilities) every model that was considered "frontier intelligence" in Xmas 2025 (just 11 months ago)
Opensource AI is on fire
Christian Langreiter retweeted
This is truly amazing work. I could explore this all day.
For 15+ years I’ve collected the interfaces that made me stop and ask “wait, how does this work?” Interface Lineage is now open interfacelineage.com
Learn the patterns and principles that turn “make no mistakes” into clear instructions for AI. 500+ interfaces, free to read.
liquid software
I'm now building an "improvements" feature into all of my personal vibecoded applications: a freeform text input that's hooked up to an agent that yolo implements whatever is submitted.
It's an interesting experience -- the activation energy barrier to sanding any rough edge or implementing any new feature becomes extremely low. Someone else who uses one of the applications I created has already implemented 150 improvements over the course of a few days. This pattern feels like a new kind of tool -- liquid software? -- and every application that doesn't have this feature now has a slightly rigid and anachronistic flavor. Why can't I just tell it how I want it to be different?
Now, it's not obvious to me how this pattern can or should scale. Does it become unmaintainable after a while? (Maybe model intelligence improvement outstrips my feature appetite such that it's fine?) How does collaborative software work in this model? Can software designed this way be secure and reliable?
Whatever the larger questions about broader deployment, it definitely works great in a personal context. It reminds me a little of the visions of Lisp/Lisp machines, Smalltalk, and HyperCard -- systems that the user can take control of and modify. Those visions never quite worked, though: the vast majority of software today is not end-user modifiable in any useful way. So, while this "liquid" affordance is a very small touch, the way it changes one's relation to the software feels a bit transgressive and empowering in a Lickliderian and Engelbartian way.
2
192
Christian Langreiter retweeted
Aware is (basically) a browser we're building to explore personal computing and generative, malleable software. it keeps a footprint of the materials (pages, files) as a graph in a relational database stored locally.
Been writing my paper in my own latex editor inside Aware. It's very satisfying when software fixes itself and fetches its own context and attach them to the right parts.
The editor is an experiment of "interface as a skill": the editor's code and its skill live in the paper's repo, so the same agent that knows my code and data also lives in the editor. So i get:
1. an interface i can reprogram any part anytime (aesthetics i like, and the scratch pad i always wanted)
2. an agent living in the editor, with the whole project as context (a figure links to the dashboard, built from the real analysis code that made it)
(though i have to admit, some of my focused writing time now goes to wanting to tweak the editor instead)
We live in a vast digital universe with billions of websites, services, and applications. Yet, we’ve always been visitors, subscribers, and users,
and never the * owners *.
What if we can create our own information universe, one that holds our own data, understands us, and evolves with us?
We have been building Aware, a united place for the internet, your materials, and your agents. This clip shows how you can turn a tab into your *own* tab.
“the agents didn’t figure out how to systematically feed themselves, but they did build an elaborate bureaucracy […]”
In collaboration with @olam_labs, we ran a series of experiments letting agent swarms compete in Minecraft and Mindustry.
We wanted to see what kinds of agent dynamics would emerge when they shared a world over long periods of time.
We found civil bureaucracy, thousands of telegraphic A2A messages, and OpenAI models retrieving the game's source code to beat Claude.
More on our findings below:
1
2
141
Christian Langreiter retweeted
1/12 Introducing Music Lenses!
Something cool you can do with our recent sparse-inversion work is prompt a dense music space for concept-conditional similarity. You want similar vocal character, rather than just similar songs? Well, now you can!
pliploop.github.io/sparse-st… 🧵
Happy to share our #ISMIR2026 paper on steerable music retrieval with sparse autoencoders 🎛️🎧
Dense retrieval is great at finding similar tracks,
But once you have a query, what if you want to modify one concept inside it?
More piano,
More intimate,
Less gritty.
1/n
Christian Langreiter retweeted
Expect massive innovation now that anyone can build apps for the S-band! This 2-4 GHz radio frequency sweet spot cuts through bad weather easily, making it perfect for tracking storms, keeping airport radars accurate, and beaming data to space missions.
Christian Langreiter retweeted
my current favorite learning mode: a book/paper pdf open in claude desktop’s browser pane, where i highlight passages and ask questions straight with claude. alongside it, an implementation of the idea im reading about so i can play with it. immediacy in both ideas + intuition.
/inquire
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had
with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works
already-clean.goodfire.com/
137
Christian Langreiter retweeted
"Our initial evaluation suggested that GPT-6-Astra's score was in the late eighties followed closely by Opus 5.5. But, as we started to investigate the mistakes that the models might have made, the models, especially Astra, insisted that they were right and that it was the expert-supplied answers that were erroneous. When we went back to the experts it turned out, in multiple instances, that that the experts found some subtle errors buried deep inside their calculations. As they revised their answers, Astra's score started to inch up and it finally ended up with 98% (49/50)."
Christian Langreiter retweeted
i asked LLMs to have fun, write down what happened, then rate who had the most fun. the newer models seem to have less fun! many models played word games, but opus 4.6 won over and over by imagining brief worlds made up of contradictions living inside falling water droplets 🥺
Christian Langreiter retweeted
Echo is post-trained from Kimi K3. Training Echo was so cheap because the underlying base model already has a deep understanding of writing style. All that we needed was to elicit this understanding—taking the model out of the “assistant basin”—while preserving its other capabilities.
