Sadat Ansari retweeted
A brief history of AI Coding since Nov 2025:
Nov 2025: Opus 4.5 releases, OpenClaw gets built
Dec 2025: community agrees that models get good enough to handle 95% of coding tasks
Jan 2026: Ralph loops get popular, early efforts on loops/orchestration
Feb: Everyone feels knackered, too much strategic decision-making, fears around cognitive debt begin
Mar: Skills explosion as community converges around easy-to-share processes (superpowers already ahead of the game here)
Apr: most SOTA devs haven't written a line of code in months
May: "The unreasonable effectiveness of HTML" - more interest in richer review surfaces
Jun: "Loop Engineering" wins vaguepost of the year, signals more hype around process
Jul: Every talk in every conference becomes "here is my software factory"
Aug: Opus 5 speaks incomprehensibly, interest in ASD-STE100 peaks
Sep: Grok Bot gets popular, more interest in long-running "manager" threads which retain context and delegate work
Oct: The promised speed gains haven't materialised, "dark factory" feels a long way off still
Nov: No-slop manifesto releases, reading the code still appears essential
TL;DR: no-one is writing code anymore, and we are still figuring out what that means
Sadat Ansari retweeted
We've given all Pro, Max, Ultra, and Team users one free full reset, across all models and limits. Use it anytime before December 10 at 2:00PM PT.
We recently fixed a few small issues that used more limits than intended, and the Fable resets didn't do much for those of you who'd already hit your weekly limits for all models. While these issues didn't affect everyone, we want to make up for the trouble.
You'll find it in Settings > Usage, or at clau.de/reset.
Sadat Ansari retweeted
I’m so glad I became an engineer (over a footballer or a doctor - other two options I had)
As an engineer, with AI you can just do anything now. Open models have gotten so good I think they’re like a month behind the closed frontier now.
In the last three days I’ve deleted 18 mac apps and rewritten them from scratch with my taste and preferences. This has increased my productivity and focus beyond what I expected.
It’s not just software btw. I’m building hardware too.
I’m again starting to lean into my electrical engineering background and having so much fun building hardware. Using Command Code to write hardware kernels that auto evolve as needed in a giant rsi loop has been such a rewarding experience.
What an exciting time to be an engineer.
I recommend that you build a couple of small apps to experience this. Start today.
Sadat Ansari retweeted
With AI, a single person with high clarity can outdo a team that lacks it. Before, there was still a chance to catch up; now, there is none.
Sadat Ansari retweeted
The gap between an average engineer and the best engineers was never quite 10x, but it was meaningful.
AI has made the gap at least 100x.
Sadat Ansari retweeted
Irrespective of whether software engineering is coming to an end or not, think of it as a roller coaster ride. You are already on it, so have fun while it lasts.
Either it crashes or lands you safely.
You have to be optimistic about technology. If things go wrong, it will be the end for everyone. If AI is here to stay and you refuse to adapt, you will be left far behind.
Your best bet is to stay positive with tech ... always :)
Sadat Ansari retweeted
software is dead - says man making software
that’s correct - says man also making software
the software engineer is dead - says man being software engineer
it’s over - says another software engineer
If you're stuck at "AI is just another tool", you're making a category error. This is not "same computer, but better". It's far more akin to hiring a bunch of extremely intelligent and capable coworkers with whom you might occasionally disagree.
Sadat Ansari retweeted
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
The only programmers who are really in trouble with the competition from artificial intelligence are the ones who insist the world today isn't all that different from the one we lived in last year.
Embrace the paradigm shift or perish.
(This has always been true.)
Sadat Ansari retweeted
btw, I also run an engineering "newspaper" curating blogs, articles, and papers on system design, databases, and applied AI.
I keep it updated every day. It publishes with a 2-day delay, but is heavily curated.
It is called tdd.cat, you might find it helpful. High signal, low noise, always :)
Here is the thing you want to keep yourself updated in tech by @arpit_bhayani
I'll try to make a habit of reading atleast a bit.
tdd.cat
Sadat Ansari retweeted
Unlike LLMs, Jev didn't invent a new concept.
Classifiers have existed for decades, with exactly the same interface → ask a question, get a probability score.
BUT, here's what the hype is all about:
- it works for *any* problem, no training required
- it's fast → you can do stuff in real-time
- it's cheap
You can see it as a democratization of classifiers. Before, only those with a huge amount of their own training data could own one. Now, you get your own at the speed of thought.
This won't disrupt the existing classifier market. Custom-trained classifiers will always beat the one-size-fits-all solution.
But this opens a whole new market for the rest of us where retail is more than good enough.
It's the same thing that happened with digital photography, Canva, 3d printing, and vibe coding.
Sadat Ansari retweeted
People hyping over Jev first understand Jev isn’t a dropin replacement for an LLM. It doesn’t generate text, but it can handle classification tasks we often use LLMs for today, without the same latency and cost. That makes it a promising complement to the model driving your agent
Sadat Ansari retweeted
You know what is funny?
UPI could theoretically be funded for 22 years if we just stopped one state's freebie scheme for a year.
And I am already being ridiculously generous with the UPI cost estimate.
Madhya Pradesh allocated ₹18,984 crore to Ladli Behna in FY2024-25.
Now look at UPI.
UPI processed roughly ₹260.56 lakh crore in FY2024-25.
It also needs massive redundancy. Multiple data centres. Retries. Fraud detection. Security. And enough spare capacity to handle huge spikes in traffic.
NPCI also uses commodity, bare-metal hardware instead of paying cloud prices for every request. (so we spent on majorly on electricity and maintenance)
Let's assume the entire UPI infrastructure costs:
$50 million a year.
That's roughly ₹430 crore.
Now let's be stupidly conservative. (for x reasons)
Double it.
₹860 crore per year.
And this ₹860 crore is supposed to cover:
> Bare-metal servers
> Multiple data centres
> 3x to 5x capacity headroom
> Failed transactions
> Retries
> Fraud detection
> Security
> Storage
> Networking
> Redundancy
> Monitoring
> Everything else
₹18,984 crore ÷ ₹860 crore = ~22 years.
So one state's allocation for ONE scheme could theoretically pay for 22 YEARS of UPI infrastructure.
We're talking about one of the largest payment systems on the planet.
And I still gave the hypothetical infrastructure bill 2x the original estimate.
The point isn't that UPI literally costs ₹860 crore a year.
The point is how fucking different the scale is. And still someone people will not understand any of it.
And its just fucking state's 1 scheme.
Now imagine the level of C----.
Sadat Ansari retweeted
I’ll admit, it’s HORRIBLE dealing with so much AI information every single day, then stepping away from X and realizing that nobody, NOBODY around me knows any of this.


























