Santi Herrero (@santihbc) header
Santi Herrero (@santihbc) profile picture

Co-founder & CTO @edpuzzle. I read the code.

Barcelona, Spain
Joined June 2009
Photo by Santi Herrero (@santihbc)Photo by Santi Herrero (@santihbc)Photo by Santi Herrero (@santihbc)Photo by Santi Herrero (@santihbc)Photo by Santi Herrero (@santihbc)Photo by Santi Herrero (@santihbc)Photo by Santi Herrero (@santihbc)Photo by Santi Herrero (@santihbc)Photo by Santi Herrero (@santihbc)Photo by Santi Herrero (@santihbc)
Santi Herrero retweeted
Engineering isn't just a means to an end. A lot of people derive satisfaction in the process of building.
8
7
2
127
5,161
Santi Herrero retweeted
My son asking me a lot of questions. It’s a distillation attack obviously.
226
1,475
129
19,537
547,584
Santi Herrero retweeted
# on shortification of "learning" There are a lot of videos on YouTube/TikTok etc. that give the appearance of education, but if you look closely they are really just entertainment. This is very convenient for everyone involved : the people watching enjoy thinking they are learning (but actually they are just having fun). The people creating this content also enjoy it because fun has a much larger audience, fame and revenue. But as far as learning goes, this is a trap. This content is an epsilon away from watching the Bachelorette. It's like snacking on those "Garden Veggie Straws", which feel like you're eating healthy vegetables until you look at the ingredients. Learning is not supposed to be fun. It doesn't have to be actively not fun either, but the primary feeling should be that of effort. It should look a lot less like that "10 minute full body" workout from your local digital media creator and a lot more like a serious session at the gym. You want the mental equivalent of sweating. It's not that the quickie doesn't do anything, it's just that it is wildly suboptimal if you actually care to learn. I find it helpful to explicitly declare your intent up front as a sharp, binary variable in your mind. If you are consuming content: are you trying to be entertained or are you trying to learn? And if you are creating content: are you trying to entertain or are you trying to teach? You'll go down a different path in each case. Attempts to seek the stuff in between actually clamp to zero. So for those who actually want to learn. Unless you are trying to learn something narrow and specific, close those tabs with quick blog posts. Close those tabs of "Learn XYZ in 10 minutes". Consider the opportunity cost of snacking and seek the meal - the textbooks, docs, papers, manuals, longform. Allocate a 4 hour window. Don't just read, take notes, re-read, re-phrase, process, manipulate, learn. And for those actually trying to educate, please consider writing/recording longform, designed for someone to get "sweaty", especially in today's era of quantity over quality. Give someone a real workout. This is what I aspire to in my own educational work too. My audience will decrease. The ones that remain might not even like it. But at least we'll learn something.
658
3,618
838
18,756
2,297,823
Santi Herrero retweeted
I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue. There's a new programmable layer of abstraction to master (in addition to the usual layers below) involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering. Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it, while the resulting magnitude 9 earthquake is rocking the profession. Roll up your sleeves to not fall behind.
2,554
7,298
2,906
55,181
17,120,183
How it started: "AI vibe coding tools will replace devs!" How it's going: "Do this: - Provide it w a detailed spec - Break down tasks to small ones - Separate dev and prod envs - Do NOT give access to the agent to prod - Never trust the agent; verify every step it takes - ...
186
465
72
6,425
672,081
Santi Herrero retweeted
“It is impossible to get better and look good at the same time. Give yourself permission to be a beginner.” — ​Julia Cameron​, The Artist’s Way
101
374
26
3,144
155,666
Santi Herrero retweeted
This is huge! This fixes the universal problem with conversational agents: hallucinations! Every company that builds customer-facing agents struggles to align them with business rules and make them consistent. If you solve this, you'll become a hero overnight. Check out Parlant, a free, open-source library taking off on GitHub. This is why it's big: 1. You have 10x more control over what your conversation agent says 2. You control how it conducts conversations 3. You control the service protocols and rules it follows 4. You control what it can and can't say Here is how Parlant's engine works behind the scenes as soon as your agent receives a question from a customer: 1. It loads the necessary domain terminology 2. It finds the relevant guidelines to answer the question 3. It invokes your tools to gather any relevant information 4. It implements self-critique to craft/evaluate its response iteratively All of this makes it very hard for an agent to hallucinate. Here is the GitHub repository: github.com/emcie-co/parlant And here is a paper showing the prompt engineering method Parlant uses behind the scenes (4.8% more accurate than Chain of Thought!): arxiv.org/abs/2503.03669
19
95
8
860
93,175
Santi Herrero retweeted
Here's a 16-hour timelapse of an embryo building a central nervous system so 23 years from now it can sell b2b SAAS
506
4,727
435
58,479
3,614,844
32
105
38
871
102,640
Yesterday this post blew up. Tons of you asked about the workflow behind it, so I’m breaking it down in this thread. Honestly, it’s super simple for how epic it looks.
Magnific Structure Reference + Runway Restyle Video = Absolute Game Changer
29
220
13
2,841
394,941
I keep hearing people talking bout not having vague requirements, but vague is at the heart of agility. You want things as vague as possible until the last responsible moment. The requirements NOT being vague is a huge red flag, and detailed up-front requirements lead to software that's riddled with bugs of the "nobody needs this" and "this isn't the right way to do it" variety.
21
23
2
185
19,870
Gracias por darnos la oportunidad de presentar @edpuzzle en #SCPNA y de esponsorizar el evento. Dejo aquí el link a las slides de la charla "Diseñando la topología de tu equipo de ingeniería" bit.ly/3WN20zU
6
1
15
883
Santi Herrero retweeted
when i was a consultant weak data modeling skills were the #1 source of problems they cause technical problems which cause business problems which cause bad solutions put in the wrong places a lot of pain can be avoided with a little more effort thinking about data models
Replying to @warrior_amp
if you’re building a booking system you may have the concept of an appointment you want to support rescheduling so you simply update the timestamp but you lose a bunch of information, for example if you want to understand how many times a customer has rescheduled in reality rescheduling is the act of marking an appointment as canceled and making a new appointment, this is a stronger model so if you think purely in terms of the product you end up with something less correct vs if you think about what’s actually going on simplified example
21
17
7
255
79,905
Most data scientists know how to train ML models inside notebooks. But very few know how to transform these notebooks into *complete* ML solutions that generate business value Wanna get there and become a top-paid ML engineer? Check out this tutorial ↓ realworldmachinelearning.car…
1
21
74
6,906
Tired of training lots of Machine Learning models, and not getting better results? 😵‍💫 This is how you solve this 🧠↓
12
127
6
546
Hi @ryanflorence how would you implement this UI in @remix_run ? There is an on scroll infinitely paginated list of videos where one from the second page is selected and shown in detail on the right. After clicking the star (1) to favorite it, the star in (2) must also be updated
1
4
It seems that for infinitely paginated lists the best option is to store a copy of the fetched items in React state. That obviously means that to implement the UI above, we would have to update that React state cache manually. I wonder if there is a more remix way to do this?🤔
2
2
Santi Herrero retweeted
Video lessons will never be the same again. Come find out why! 🗓 1/20/2022 @ 7:30 EST 🔗 https://xitter.gq/t.co/jtqXerID8z This is an #EdpuzzleLive you don’t want to miss. 💛💛💛 Sneak peek below! 👇 👀
1
13
3
49
¡Comienza el Black Friday de CodelyTV Pro! 🚀 😱 ¡100€ de descuento en el plan anual! 🎯 Cursos de SOLID, DDD, Hexagonal, Frontend 🔜 TDD, Arquitectura Front, DDD en TS… ✅ DevOps, Tooling… ¡Cursos TOP! 🔥 ¡Aprovecha la oferta antes de que acabe! ⮕ codely.tv/pro/blackfriday?ut…
1
26
1
50