sumitkumar

prompt: create a qr code to https://www.anthropic.com

response: https://chatgpt.com/backend-api/estuary/content?id=file_0000...

result: FAIL

I feel it is about being disinterested than about being good. the ones who were not interested(whether good or bad) and were trapped in a job are liberated and happy to see it be automated.

The ones who are frustrated are the ones who were interested in doing(whether good or bad) but are being told by everyone that it is not worth it do it anymore.

I have seen more reactions of people about this tech than actual implementations made possible which pushed the boundaries further. It is an amplifier of technical debt in mostly naive(people experienced in bad patterns) user base.

Take anthropic for example, they have created MCP/claude code.

MCP has the good parts of how to expose an API surface and also the bad parts of keeping the implementation stuck and force workarounds instead of pushing required changes upstream or to safely fork an implementation.

Claude code is orders of magnitude inefficient than plainly asking an llm to go through an architecture implementation. The sedentary black-box loops in claude code are mind bending for anyone who wants to know how it did something.

And anthropic/openai seems to just rely of user momentum to not innovate on these fundamentals because it keeps the token usage high and as everyone knows by now a unpredictable product is more addictive than a deterministic one.

We are currently in the "Script Monkey" phase of AI dev tools. We are automating the typing, but we haven't yet automated the design. The danger is that we’re building a generation of "copy-paste" architects who can’t see the debt they’re accruing until the system collapses under its own weight.

One more thing to add is that the external communication code/infra is not written/managed by the agents and is part of a vetted distribution process.

I was also startled when I learned about the human ancestor who was the first to see a mirror.

The brilliance of AI is that it copies(mirrors) imperfectly and you can only look at part_of_the_copy(inference) at a time.

It seems it is true for gemini because they have a humongous sparse model but it isn't so true for the max performance opus-4.5/6 and gpt-5.2/3.

It is not about making it yourself but a tradeoff between how much it can be controlled and how much has seen the real world. Adding requirements learned by mistakes of others is slower in self-controlled development vs an open collaboration vs a company managing it. This is the reason vibe-coded(initial requirements) projects feels good to start but tough to evolve(with real learnings).

Vibe-coded projects are high-velocity but low-entropy. They start fast, but without the "real-world learnings" baked into collaborative projects, they often plateau as soon as the problem complexity exceeds the creator's immediate focus.

Microservices is bad for teams without discipline to implement "separation of concerns". They hope that physical network boundaries will force the discipline they couldn't maintain in a single codebase.

While microservices force physical separation, they don't stop "Spaghetti Architecture." Instead of messy code, you end up with "Distributed Spaghetti," where the dependencies are hidden in network calls and shared databases.

Microservices require more discipline in areas like:

Observability: Tracking a single request across 10 services. Consistency: Dealing with distributed transactions and eventual consistency. DevOps: Managing N deployment pipelines instead of one.

For most teams Modular monolith is often the better "first step." It enforces strict boundaries within a single deployment unit using language-level visibility (like private packages or modules). It gives you the "Separation of Concerns" without the "Distributed Spaghetti" network tax.

pydantic/pydanticAI in builder mode or llamaindex in solution architect mode.

AI/non-AI/human/hybrid: It doesn't matter which one is the writer.

It's the reader who decides how good the writing is.

The joy which the writer gets by being creative is of no consequence to the reader. Sacrifice of this joy to adopt emerging systems is immaterial.

Even thin single use plastic works. The first time I saw it it was surreal.

So this is about customer support. Google supports by the customer by a better product but minimal manual support for issues later.

AWS has an organically evolved bad product which has been designed by long line of six page memos but a manual support in case things get too confusing or the customer just need emotional support.

I wanted to see how far it will go. I started with asking it to simple test app. It said it is a great idea. And asked me if I want to do market analysis. I came back later and asked it to do a TAM analysis. It said $2-20B. Then it asked if it can make a one page investor pitch. I said ok, go ahead. Then it asked if I want a detailed slide deck. After making the deck it asked if I want a keynote file for the deck.

All this while I was thinking this is more dangerous than instagram. Instagram only sent me to the gym and to touristic places and made me buy some plastic. ChatGPT wants me to be a tech bro and speed track the Billion dollar net worth.

1) Word Ladder: Chaos to Order

2) Shortest word ladder: Chaos to Order

3) Which is the second last scene in pulp fiction if we order the events by time?

4) Which is the eleventh character to appear on Stranger Things.

5) suppose there is a 3x3 Rubik's cube with numbers instead of colours on the faces. the solved rubiks cube has numbers 1 to 9 in order on all the faces. tell me the numbers on all the corner pieces.

Here is the conversation link with gemini. https://g.co/gemini/share/d253e2ef286c

Well, I was not comparing but it was just an observation.

I understand Magic has more constraints on which libraries it can use and probably is for forms-flow kind of workflows and not for managing complex states of games.

Hi, Thank you for sharing.

I tried this prompt.

``` create a Rubik's cube app with all available moves and show the cube and the animations. add a scrambler and a solver. Also add timer to time the moves. ```

I got this.

https://www.magicpatterns.com/c/psesccrmk41jibfhwp7wh1

Which looks like a good starting point but doesn't work at all. After this it is daunting to look at code. I still have to figure out how to tell the chatbox to fix it.

Gemini 2.5 pro did much better in one shot. (the prompt was different and without the scrambler/solver/timer)

https://sumitkumar.github.io/llmgenerated-static/

It is free. though it takes your data for future training.

https://firebase.google.com/docs/gemini-in-firebase#:~:text=...

Firebase Studio is an agentic, cloud-based development environment that gives you powerful tools and AI agents directly in your browser. With Firebase Studio, you can prototype, build, test, publish, and iterate on full-stack AI apps from a single place.

I like to think that the bacteria are only on the outermost layer of the body, i.e. skin. It just happens so that the respiratory and the digestive systems are the exterior part of the body which are inside our body. In other words epithelial cells mark the boundary of inside and outside and bacteria are usually tolerated on the outside and not inside.

Using this method one can have multiple conversations with self with different contexts. I use one to keep the important docs handy like ongoing travel tickets etc. Another one for Shopping list. and another for saving links and watch later.

Agree. Expressed well and measured. And it is learned by expressing badly first and then one gets better. When kids have a tantrum it is a good opportunity to make them aware of it and allow them modulate it. But if one doesn't let them express or gives no attention to their expression it can foster other emotions and delays the learning of modulation.

Unconstrained expression of anger is usually a result of long term suppression and then falling into the trap that suppression doesn't work so modulation will also not.

It is difficult to model the anger and resolution patterns easily but I will try. Say there is a discomfort/cause/trauma for anger. In a way it is a stress response to prepare one to fight or make a change. If one adds a little anger to a fight their response improves. And if one doesn't use the anger as a signal, the signal gets louder next time. During an acute stress response it is better to use the anger energy and express yourself and win/lose/stall the fight rather than mute/lose the fight and in later revisits to the incident give in to the anger because later there is no outlet or easy resolution except letting go. The helplessness of not acting gives rise to the emotions of regret/revenge and impact self-worth/identity when the action is delayed. And these emotions are more damaging than anger as they can influence our positive actions in other areas.

Now in our current world not every incidence of anger is because of a conflict but follows the same pattern. To talk about the bad weather is better than grumbling about it. Grumbling about it is better than grinding your teeth. And expression does not mean give in to the anger without awareness, so it is not okay to direct the rage one felt in the workplace to their family members or to kick the tyre of a car.

Expressed anger/emotion is okay, bottled up anger/emotion is not good. And all restraint must hit the emotion sink without delay. So don't keep emotional debt. Settle it right away or forget it forever.

I have a feeling that soon we will have models which will predict the future better than humans and then the humans will stop predicting it and we will lose all insights into how to predict the future. at least the models will not make mistakes. /s

They got seed round recently.

https://techcrunch.com/2024/03/05/competition-in-ai-video-ge...

Not as good as sora demos but this is something which can be tried right away.

The original charter is nothing more than a marketing copy. And companies are legally allowed to change their marketing copy over time and are not bound to stick to it in behavior. The marketing was for the investors and they should be the first to know that such promises are subject to how reality unfolds. In other words a team can raise money by promising milestones but they are allowed to pivot the whole business and not just abandon milestones if the reality of the business demands it.

The LLMs are generating training data at a faster rate than SO. All the prompts and the responses will eventually be 99.99% of the training data.

It is not yet proven that electrons need to flow from point A to point B to transfer electric energy. There is local movement but not in the sense that electrons are flowing through a hose to transfer power.

Protons are electricity. But slow. All acid/base reactions. Proton gradients and pumps in the biological cells all work on slow proton electricity.