Simone D'Angelo

[Simone D'Angelo @simokobe24]

@calebfahlgren Cool, which prompt did you use to get those nice diagrams and figures?

[Lorenzo Ruffino @Ruffino_Lorenzo]

Per avere un metro di paragone

Aiuti militari per l'Ucraina: 3 miliardi
Sussidi a cinema e serie TV nello stesso periodo: 3,1 miliardi.

[Simone D'Angelo @simokobe24]

@_justmba @aloo_jira This is backend principle, not postgres. I cannot find it

[Lewis Hamilton @LewisHamilton]

REMEMBER WHO YOU ARE

[Andrew Ng @AndrewYNg]

Coding agents are accelerating different types of software work to different degrees. When we architect teams, understanding these distinctions helps us to have realistic expectations. Listing functions from most accelerated to least, my order is: frontend development, backend, infrastructure, and research.

Frontend development — say, building a web page to serve descriptions of products for an ecommerce site — is dramatically sped up because coding agents are fluent in popular frontend languages like TypeScript and JavaScript and frameworks like React and Angular. Additionally, by examining what they have built by operating a web browser, coding agents are now very good at closing the loop and iterating on their own implementations. Granted, LLMs today are still weak at visual design, but given a design (or if a polished design isn’t important), the implementation is fast!

Backend development — say, building APIs to respond to queries requesting product data — is harder. It takes more work by human developers to steer modern models to think through corner cases that might lead to subtle bugs or security flaws. Further, a backend bug can lead to non-intuitive downstream effects like a corrupted database that occasionally returns incorrect results, which can be harder to debug than a typical frontend bug. Finally, although database migrations can be easier with coding agents, they’re still hard and need to be handled carefully to prevent data loss. While backend development is much faster with coding agents, they accelerate it less, and skilled developers still design and implement far better backends than inexperienced ones who use coding agents.

Infrastructure. Agents are even less effective in tasks like scaling an ecommerce site to 10K active uses while maintaining 99.99% reliability. LLMs' knowledge is still relatively limited with respect to infrastructure and the complex tradeoffs good engineers must make, so I rarely trust them for critical infra decisions. Building good infrastructure often requires a period of testing and experimentation, and coding agents can help with that, but ultimately that’s a significant bottleneck where fast AI coding does not help much. Lastly, finding infrastructure bugs — say, a subtle network misconfiguration — can be incredibly difficult and requires deep engineering expertise. Thus, I’ve found that coding agents accelerate critical infrastructure even less than backend development.

Research. Coding agents accelerate research work even less. Research involves thinking through new ideas, formulating hypotheses, running experiments, interpreting them to potentially modify the hypotheses, and iterating until we reach conclusions. Coding agents can speed up the pace at which we can write research code. (I also use coding agents to help me orchestrate and keep track of experiments, which makes it easier for a single researcher to manage more experiments.) But there is a lot of work in research other than coding, and today’s agents help with research only marginally.

Categorizing software work into frontend, backend, infra, and research is an extreme simplification, but having a simple mental model for how much different tasks have sped up has been useful for how I organize software teams. For example, I now ask front-end teams to implement products dramatically faster than a year ago, but my expectations for research teams have not shifted nearly as much.

I am fascinated by how to organize software teams to use coding agents to achieve speed, and will keep sharing my findings in future posts.

[Original text: https://t.co/rnnVWqebVe ]

[Alfonso Fuggetta @AlfonsoFuggetta]

Non riuscivo più a ritrovare questo tweet. Importantissimo. #daleggere

[Ronan Berder (SF + SG) @hunvreus]

Talking to smarter folks than me, I'm convinced many of the AI folks in my timeline are full of shit.

Nobody is "running 20 agents over night" and building stuff for actual users. Maybe some are building internal tools or disposable software. Maybe.

But building software people like using? That doesn't get hacked on day one or blow up after the 3rd user? Nope.

I don't even understand what that's supposed to look like. Do you work out a 57 pages document that perfectly describes what you want to build and then summon 14 agents and have them run wild for 6 hours? And what comes out on the other end isn't a broken pile of shit?

Nope. Not buying it.

PS: it may also be that I have an IQ of 82 and can't figure it out.

[pulkit mittal @pulkit_mittal_]

Python developers are mostly mediocre

Worked with a guy a few years ago on a project.

We were on a tight deadline and he was moving fast, shipping features non-stop.

At first, I was impressed.
Then I looked at the code. Just imports, libraries, shortcuts.Everything abstracted away. No clue what’s happening underneath.

I thought maybe he’s just optimizing for speed.But then it hit me:

That’s how most people use Python.

No understanding of memory
No sense of performance
No depth in fundamentals

In C++ or Java, you can’t get away with that.

Just write, run, ship
And somehow this is called productive.

[Uncle Bob Martin @unclebobmartin]

@plainionist Learn the basics. Just as before. Learn them very well. Write assembler, C, Java, Ruby. Learn algorithms and data structures. Read the old classics.

And then start using agents.

Novices with power tools tend to lose fingers.

[Simone D'Angelo @simokobe24]

@BenjDicken I love what you're doing with your channel. Tired of reading about AI everywhere. DBs are amazing

[Dmitrii Kovanikov @ChShersh]

After programming for 16 years, I noticed that Software Engineer mentality slowly shifted from “produce great code” to “tolerate shit code”

[ThePrimeagen @ThePrimeagen]

i am completely convinced the majority of LLM usage is spam or scams

The technology has been a net negative on society thus far

[Simone D'Angelo @simokobe24]

@_adityaa21 which topics "basics" include?

[La Gazzetta Ferrari @GazzettaFerrari]

"Lewis, remember who you are mate. You did it. You will do it again. So much love for you man. So much love." 🤍

[ThePrimeagen @ThePrimeagen]

learn to code

[Mario Seminerio @Phastidio]

Il ribrezzo, nel suo significato più pregnante.

[Vittorio Emanuele Parsi @VEParsi1]

Incapace di bloccare l'aggressore, Trump cerca di bloccare l'aggredito. Un vigliacco e un grande europeo, vittima di un agguato mafioso alla Casa Bianca. E Meloni peggio di Ponzio Pilato. Vergogna.

[Andrej Karpathy @karpathy]

New 3h31m video on YouTube:
"Deep Dive into LLMs like ChatGPT"

This is a general audience deep dive into the Large Language Model (LLM) AI technology that powers ChatGPT and related products. It is covers the full training stack of how the models are developed, along with mental models of how to think about their "psychology", and how to get the best use them in practical applications.

We cover all the major stages:
1. pretraining: data, tokenization, Transformer neural network I/O and internals, inference, GPT-2 training example, Llama 3.1 base inference examples
2. supervised finetuning: conversations data, "LLM Psychology": hallucinations, tool use, knowledge/working memory, knowledge of self, models need tokens to think, spelling, jagged intelligence
3. reinforcement learning: practice makes perfect, DeepSeek-R1, AlphaGo, RLHF.

I designed this video for the "general audience" track of my videos, which I believe are accessible to most people, even without technical background. It should give you an intuitive understanding of the full training pipeline of LLMs like ChatGPT, with many examples along the way, and maybe some ways of thinking around current capabilities, where we are, and what's coming.

(Also, I have one "Intro to LLMs" video already from ~year ago, but that is just a re-recording of a random talk, so I wanted to loop around and do a lot more comprehensive version of this topic. They can still be combined, as the talk goes a lot deeper into other topics, e.g. LLM OS and LLM Security)

Hope it's fun & useful!
https://t.co/75mXcUBI8L

[Simone D'Angelo @simokobe24]

Non stiamo imparando più niente https://t.co/CttSRYbwKC via @YouTube

[Cecilia Sala @ceciliasala]

Ho la fotografia più bella della mia vita, il
cuore pieno di gratitudine, in testa quelli che alzando lo sguardo non possono ancora vedere il cielo. Non ho mai pensato, in questi 21 giorni, che sarei stata a casa oggi. Grazie