Farzad Haghighat

Idealist 📏 Life-Long Learner 📖 Analytical Data Geek 📈 Developer ⌨️

[Alex Veremeyenko @alex_verem]

MIT just made vibe coding an official part of engineering 💀

MIT just formalized "Vibe Coding" – the thing you've been doing for months where you generate code, run it, and if the output looks right you ship it without reading a single line.

turns out that's not laziness. it's a legitimate software engineering paradigm now.

they analyzed 1000+ papers and built a whole Constrained Markov Decision Process to model what you thought was just "using ChatGPT to code."

they formalized the triadic relationship: your intent (what/why) + your codebase (where) + the agent's decisions (how).

which means the shift already happened. you missed it. there was no announcement, no transition period. one morning you woke up writing functions and by lunch you were validating agent outputs and convincing yourself you're still "a developer."

but you're not. not in the way you used to be.

here's what actually broke my brain reading this 42-page survey:

better models don't fix anything. everyone's obsessing over GPT-5 or Claude 4 or whatever's next, and the researchers basically said "you're all looking at the wrong variable."

success has nothing to do with model capability. it's about context engineering – how you feed information to the agent. it's about feedback loops – compiler errors + runtime failures + your gut check. it's about infrastructure – sandboxed environments, orchestration platforms, CI/CD integration.

you've been optimizing prompts while the actual problem is your entire development environment.

they found five models hiding in your workflow and you've been accidentally mixing them without realizing it:

- Unconstrained Automation (you just let it run),
- Iterative Conversational Collaboration (you go back and forth),
- Planning-Driven (you break tasks down first),
- Test-Driven (you write specs that constrain it),
- Context-Enhanced (you feed it your entire codebase through RAG).

most teams are running 2-3 of these simultaneously.

no wonder nothing works consistently.

and then the data says everything:
productivity losses. not gains. losses.

empirical studies showing developers are SLOWER with autonomous agents when they don't have proper scaffolding.

because we're all treating this like it's autocomplete on steroids when it's actually a team member that needs memory systems, checkpoints, and governance.

we're stuck in the old mental model while the ground shifted beneath us.

the bottleneck isn't the AI generating bad code.

it's you assuming it's a tool when it's actually an agent.

What this actually means (and why it matters):

→ Context engineering > prompt engineering – stop crafting perfect prompts, start managing what the agent can see and access

→ Pure automation is a fantasy – every study shows hybrid models win; test-driven + context-enhanced combinations actually work

→ Your infrastructure is the product now – isolated execution, distributed orchestration, CI/CD integration aren't "nice to have" anymore, they're the foundation

→ Nobody's teaching the right skills – task decomposition, formalized verification, agent governance, provenance tracking... universities aren't preparing anyone for this

→ The accountability crisis is real – when AI-generated code ships a vulnerability, who's liable? developer? reviewer? model provider? we have zero frameworks for this

→ You're already behind – computing education hasn't caught up, graduates can't orchestrate AI workflows, the gap is widening daily

the shift happened. you're in it. pretending you're still "coding" is living in denial.

[Hamed @Hamed]

معرفی پروژه فارسی چک لیست امنیت در اینترنت https://t.co/fxDzeC8A9D

[Farzad Haghighat @Haghighat]

@ffahima ممنون فهیما! خیلی کوچیکه دنیا :)
اگه رفتی حتما نظرت رو بگو

[Farzad Haghighat @Haghighat]

@kiawisherman باگ نیست. حمله است. یه نفر که نباید، شماره موبایلت رو پیدا کرده. اینم ببین:
https://t.co/dY6xcOjb2i

[jadi @jadi]

طبق کامنت ها یه نظریه دقیقتر داریم: یه نفر از این بمب های اسمسی درست کرده که به این سایت ها درخواست ریست رو شماره فلان می دن. فقط خنده اش اینه که من احتمالا تو هیچکدوم از این سایت ها اکانت ندارم. واقعا اسمس می دن بدون ثبت نام؟ (: شایدم کد ثبت نامه (: به هرحال اگر اینه باحاله

[Farzad Haghighat @Haghighat]

@pourmandmhd یه دنیا تبریک محمود جان!

[Farzad Haghighat @Haghighat]

@bdsams Do you have any ETA for the Steam release of Start 11?

[Farzad Haghighat @Haghighat]

@ZahraRassar @ranaakhoondi ماشالله، حسابی سر خودت رو شلوغ کردی!

[Farzad Haghighat @Haghighat]

@JavidIzadfar قطعا Netflix. دیزنی پلاس به تنهایی اصلا قابل مقایسه نیست. اگه اون پکیجی که Hulu داره رو هم بگیری همچنان Netflix کاتالوگ بزرگتر و جذاب تری داره.

[Farzad Haghighat @Haghighat]

@mohisanisel فکر می کنم این به کارت بیاد:
https://t.co/3x0GXrjw00

[Farzad Haghighat @Haghighat]

@callmearef منطقی تر بود گزینه اول می نوشتی ۲ تا پیکسل ۵ تا قیمت هم لحاظ بشه.

[Farzad Haghighat @Haghighat]

@AtiyehMSh بنویس تجربیاتت رو به نظرم

[Farzad Haghighat @Haghighat]

@ZahraRassar @Snapp_Team

[webdevjey @webdevjey]

خب اینم از این، کتاب مجموعه سوالات استخدامی ری‌اکت بعد ۴ماه تقریبا تمومه. کار خفنی که میگفتم تبدیل md به بقیه چیزا با Latex بود 😎 ۲۰۰ صفحه رایگان :
Github : https://t.co/grRLGul6WU
Virgool: https://t.co/KL5X6QV4qS
#ريتوييت_لطفا

[Farzad Haghighat @Haghighat]

@davoodtr تبریک میگم داوود جان 🥲

[Farzad Haghighat @Haghighat]

@ZahraRassar تاریخ ویدیو رو ببین تا بفهمی این کمپین رو از چقدر وقت قبل شروع کرده تیم تبلیغات وارنر بروس
https://t.co/gIyFwnyKCa

[Farzad Haghighat @Haghighat]

@ali_ajoudanian به نظر میاد اپیک کامل آماده بوده و برای اپل تله گذاشته (فعال کردن نحوه پرداخت مستقیم) و می دونسته اپل واکنش نشون میده. علاوه بر این ویدیو یه دادخواست ۱۰۰ صفحه ای هم آماده داشته برای شکایت که اون رو دیگه قطعا نمیشه تو ۴۸ ساعت آماده کرد.

[Farzad Haghighat @Haghighat]

@damonist_org عجب حافظه ای داری علی. مخلصم در ضمن 😀

[Farzad Haghighat @Haghighat]

@Eddie_CooRo احیانا یک ماهه نمی خوای بخری؟ گویا یه همچین محدودیتی هست برای یک ماهه ولی ۳ و ۱۲ ماهه این اجبار رو نداره