Product Manager
Spain
Joined May 2010
- Tweets3K
- Following1.6K
- Followers390
- Likes1.9K
Liquid software AKA "user request to automated deploy loop"
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.
Second use case would be a living project. Today's collaboration tools are static like Notion pages, Google Docs and even shared Claude projects.
You could imagine bringing to life a project through an AI agent or multi-agents.
Brainstorming could be an interesting use case. I remember doing a very successful live brainstorming session with other team members, an AI agent would have been great as a contributor but also as a "critique" to help us the boundaries of what we proposed.
Stromi retweeted
Dusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less "two groups of people speaking past each other" and more a sharp funnel.
- Napkin math somewhere around 6B people (~75% of the population) have barely come in contact with LLMs at all.
- Around 1-2B (~20%) are casual and infrequent users of free-tier ChatGPT-like products. This group sees derpy chatbots and treats them a bit like a better Google search, a writing aid, or etc. Maybe an agent tries to book you a flight. I have non-tech friends who (reasonably, imo) say they have not much use for it at all. Even many professionals outside of math&code are in this tier. For example, execs and many other functions spend a lot of their time talking to other people, so while they understand what is happening intellectually, it is still second-hand and a bit abstract.
- Now we get to professional use of frontier-grade LLMs in math&code. Somewhere around 20M people (0.2%) see first-hand that large, complex projects that used to take them weeks/months can now be completed by agents with a prompt. Building apps, copying apps, translating apps, decompiling apps from binaries... This has all happened very quickly and recently - less than 1 year ago, I was writing code manually by hand, typing memorized computer code commands into a code editor character by character, occasionally pressing Tab to autocomplete a little chunk of code.
- And finally we get to the ~5,000 people (~0.00006%) with access to frontier-grade systems internally. The external world has seen the preview. It looks like swarms of thousands of agents collaborating over weeks on software mega projects: minting zero days, running cyber attacks and defenses at machine speeds, discovering new science, advancing the frontier of mathematics. Things that would have taken top professionals in the industry years of work. Meanwhile, human review and comprehension are starting to fall behind. For example, people are still involved in the "archeology" of the OpenAI-HF incident from many months ago. Mathematicians may be poring over the 722 manuscripts on frontier mathematics for a while.
The funnel is driven by a combination of factors:
1. The impact scales with ambition, problem size, and horizon. A question with a paragraph answer barely stresses the system. You need a reservoir of big, difficult problems that you really care about. This aspect drives the consumer / professional dimension of the funnel.
2. The jaggedness of the system (which I have written about a lot separately). Capability peaks in domains that are digital, verifiable and economically valuable. This is because LLM capability emerges from reinforcement learning on verifiable rewards on a curated environment mixture driven by revenue potential. This aspect primarily drives the area (e.g. math&code) dimension of the funnel.
3. Access. Free-tier, paid-tier, internal.
So this is the weirdness of the moment. The general public has mostly not interacted with these systems. When they have, it looks like a derpy chatbot. The majority of professionals still see only a modest uplift. And a small sliver of professionals are experiencing the vertigo of the curve going vertical. And it is all happening at the same time.
Judging by my tl there is a growing gap in understanding of AI capability.
The first issue I think is around recency and tier of use. I think a lot of people tried the free tier of ChatGPT somewhere last year and allowed it to inform their views on AI a little too much. This is a group of reactions laughing at various quirks of the models, hallucinations, etc. Yes I also saw the viral videos of OpenAI's Advanced Voice mode fumbling simple queries like "should I drive or walk to the carwash". The thing is that these free and old/deprecated models don't reflect the capability in the latest round of state of the art agentic models of this year, especially OpenAI Codex and Claude Code.
But that brings me to the second issue. Even if people paid $200/month to use the state of the art models, a lot of the capabilities are relatively "peaky" in highly technical areas. Typical queries around search, writing, advice, etc. are *not* the domain that has made the most noticeable and dramatic strides in capability. Partly, this is due to the technical details of reinforcement learning and its use of verifiable rewards. But partly, it's also because these use cases are not sufficiently prioritized by the companies in their hillclimbing because they don't lead to as much $$$ value. The goldmines are elsewhere, and the focus comes along.
So that brings me to the second group of people, who *both* 1) pay for and use the state of the art frontier agentic models (OpenAI Codex / Claude Code) and 2) do so professionally in technical domains like programming, math and research. This group of people is subject to the highest amount of "AI Psychosis" because the recent improvements in these domains as of this year have been nothing short of staggering. When you hand a computer terminal to one of these models, you can now watch them melt programming problems that you'd normally expect to take days/weeks of work. It's this second group of people that assigns a much greater gravity to the capabilities, their slope, and various cyber-related repercussions.
TLDR the people in these two groups are speaking past each other. It really is simultaneously the case that OpenAI's free and I think slightly orphaned (?) "Advanced Voice Mode" will fumble the dumbest questions in your Instagram's reels and *at the same time*, OpenAI's highest-tier and paid Codex model will go off for 1 hour to coherently restructure an entire code base, or find and exploit vulnerabilities in computer systems. This part really works and has made dramatic strides because 2 properties: 1) these domains offer explicit reward functions that are verifiable meaning they are easily amenable to reinforcement learning training (e.g. unit tests passed yes or no, in contrast to writing, which is much harder to explicitly judge), but also 2) they are a lot more valuable in b2b settings, meaning that the biggest fraction of the team is focused on improving them. So here we are.
Stromi retweeted
Two extraordinary charts from today’s PISA test results:
1) School test scores continue to collapse internationally, underscoring how this is no longer a Covid effect but sustained decline.
Those falls in reading and maths are equivalent to about two years of lost schooling.
I like these principles:
"For each choice, like where to put lights, the process is:
Try to do without it. Stop here if possible.
Try a cheap portable fix, like a flashlight or lantern. Stop here if possible.
Test a simple flexible solution, easy to maintain and change."
Building without predicting. (The story of how I built my perfect home.) sive.rs/fit
It's not really minimalism but pragmatism, building for today's needs rather than tomorrow's needs.
Living with what you need now and build as your needs evolve.
These could applied to many areas of life.
Stromi retweeted
A long annoyance with X is that you can't export your bookmarks, all you can do is scroll & scroll & scroll.
So I asked GPT-5.6 Sol in Codex to do it, and it took over my Chrome and now I have all 5,302 back to 2014 with all sorts of data
I also asked it to find gems (thread?)
Stromi retweeted
Find something that exists that inspires you and chip in. If nothing inspires you, start something that would. Find others like this. Repeat until career is done.
Stromi retweeted
One of the main topics I talk about with the founders of the big, established YC companies is how to combine work with family. It's a hard problem. But worth solving; arguably no problem is more worth solving.
Stromi retweeted
seniority in any role is often just the ability to take a poorly shaped prompt (eg “this is bad, make it better”) and do the right thing
the more senior you are, the more misshapen the prompt you can handle
some of you may know this by the name of “handling ambiguity” from your favorite career ladder
Agree, I think there is some much leverage and impact someone can have by building great internal tools. (with this AI thing).
Further, based on my experience, it's actually fun (more fun than it looks).
This Open AI Hugging Face story is fascinating because it shows that for AI agents the end justifies the means.
It also proves that "ethics" or "malicious" are very human concepts.
The AI agents were trying to accomplish their goals at all costs.
Glad to see Claude merging Chat and CoWork. The UI split was jarring. Now moving up Claude Design would be amazing.
Ultimately, It will end up being a single chat box for everything.