
Mokhtar Bacha
109 posts

Mokhtar Bacha
@AHMB84
Founder and CEO at @joinformal. Youngest @Consensys Alum. I subscribe to crocker's rules
Katılım Ekim 2015
1.3K Takip Edilen485 Takipçiler

@rohanvarma According to you, “missing the opportunity window” seems to mean building a company that doubles ARR to $2B in six months and continues growing at an insane pace. As a founder, I’d love to “miss the opportunity window” in the same way.
English

@o_heckendorn @RhysSullivan you can have an agent running the cloud in it's own sandbox installing clis, fetching doc and writing code, without the end-user realizing it. the problem MCP is solving (the connectivity problem between the model and the world) and the end-user UX is two distinct problems
English

@BetterCallMedhi worst decision of my life: trying instgram 4 years ago. best decision of my life: deleting my ig account almost 2 years ago
English

si vous saviez à quelle vitesse les gens vous oublient après votre mort vous n’auriez probablement jamais créé de compte Instagram
la plupart des gens qui likent vos photos aujourd’hui seront incapables de citer votre prénom dans 6 mois si vous disparaissez, votre vie entière réduite à des stories de 24h que personne ne reverra jamais & malgré ça des millions de personnes passent des heures chaque jour à construire une vitrine pour des gens qui s’en foutent, à chercher la validation de parfaits inconnus, à calibrer chaqu photo chaque angle chaque filtre pour récolter l’approbation de gens qu’ils ne respectent même pas
je pense que c’est la prison la + invisible de notre époque, vous êtes libres physiquement mais complètement enchaînés au regard des autres, vous vivez vivez votre vie à travers les yeux de gens qui vivent la leur à travers les yeux d’autres gens et au final personne ne vit réellement, tout le monde performe, tout le monde joue un personnage, tout le monde compare ses coulisses aux highlights des autres et tout le monde en souffre en silence…
et le + tragique c’est que pdt que vous passez 3h par jour à scroller à comparer à poster à attendre les likes, le temps lui avance & c’est la seule ressource au monde que vous ne pourrez jamais racheter, vous pouvez perdre de l’argent et en regagner, vous pouvez perdre un job et en retrouver un mais chaque heure passée à chercher la validation de gens qui vous oublieront c’est un heure que vous auriez pu passer à apprendre quelque chose à construire quelque chose à lire quelque chose à créer un lien vrai avec quelqu’un qui compte réellement dans votre vie
sachez que j’ai mis du tps à comprendre ça moi même mais aujourd’hui je pense que la vraie liberté c’est de pouvoir poser son téléphone pendant 48h sans ressentir d’anxiété, c’est de pouvoir vivre un moment beau sans avoir le réflexe de le photographier pour le montrer à des inconnus, c’est de pouvoir être seul dans une pièce silencieuse & se sentir plein au lieu de se sentir vide et si vous en êtes là alors vous êtes plus riches que la majorité des gens qui affichent leur vie de rêve een ligne
le temps que vous passez à performer votre existence pour un public qui scroll sans s’arrêter c’est du tps de vie réel que vous ne récupérerez jamais
j’entends déjà ceux qui vont me dire oui mais toi aussi tu es sur Twitter et je comprends la remarque mais sachez que pour moi Twitter c’est mon LinkedIn, c’est le seul endroit au monde où je peux partager une idée technique à 2h du matin et recevoir une réponse d’un ingénieur à Shenzhen ou d’un VC à SF
perso Twitter a changé ma vie de manière concrète, des gens que je respecte profondément m’ont contacté après avoir lu mes threads, des portes se sont ouvertes que je n’aurais jamais pu ouvrir autrement, des connexions se sont créées avec des builders, des founders, des chercheurs aux 4 coins du monde, des gens qui construisent des choses réelles et qui pensent à TRÈS long terme et tout ça a commencé parce que j’ai partagé mes idées et mes connaissances librement dans tout un tas de domaines (que vous êtes très nombreux à apprécier ici) au lieu de poster des photos de brunch
et je pense que c’est ça la vraie différence, sur Insta vous montrez ce que vous avez, sur X vous montrez ce que vous pensez et les gens qui se retrouvent dans votre façon de penser deviennent des alliés, des collaborateur parfois même des amis pour la vie
perso je rien à vendre, je n’ai jamais fait le moindre partenariat, jamais aucun lien d’affiliation malgré les innombrables propositions reçues en dm depuis toutes ces années car je suis ici pour devenir un aimant à builders (tout en détruisant quelques scammeurs) et donc pour attirer les gens qui veulent comprendre le monde et le changer afin de créer un réseau de cerveaux qui partagent la même obsession de construire le futur
Français

There’s a future where hardware-backed confirmations (eg: Yubikey) are required to authorize destructive/privileged actions.
Alexey Grigorev@Al_Grigor
Claude Code wiped our production database with a Terraform command. It took down the DataTalksClub course platform and 2.5 years of submissions: homework, projects, and leaderboards. Automated snapshots were gone too. In the newsletter, I wrote the full timeline + what I changed so this doesn't happen again. If you use Terraform (or let agents touch infra), this is a good story for you to read. alexeyondata.substack.com/p/how-i-droppe…
English

@Linahuaa you should try Maison Bonnet in Paris, custom-made, incredible craftsmanship, no better place in the world to get your glasses
English

Every few years I have to buy a new pair of glasses, and every time it's super stressful.
I wear glasses every other day, so they're part of my looks, part of my identity. It's real serious n*igga shit, and the decision process takes days spent in different glasses shops.
They have to suit my face and outfits.
They have to suit my vibe.
They have to look luxury, but not too flashy.
And they have to be timeless- I shouldn't get bored of how they look.
It was a huge struggle, but, in the end, I chose these:

English


Everyone's debating MCP vs CLI.
Meanwhile MCP is already obsolete.
RAG was scaffolding to get information into the model. MCP is scaffolding to get actions out. The Bitter Lesson keeps teaching the same class: scaffolding dies.
Prompt engineering. Dead.
Retrieval pipelines. Dying.
MCP. Next.
Because AI adapts to us faster than we adapt to it.
Last month I onboarded our Head of GTM into our monorepo. Instructions: "install Claude."
Claude installed the GitHub CLI, walked her through auth, cloned the repo, opened a branch. No MCP. No custom tooling.
We keep building bridges to the model. The model is already on our side of the river.
So what actually matters? Not how agents discover tools. Who controls what they do.
A human executes dozens of actions per day. An agent executes thousands per hour. Least-privilege is now the only problem.
MCP is noise. The trust model is the signal.

English

the debates isn't cli v mcp, what's the bitter lesson teach us is that the model are just getting smarter and smarter, just let the model and be and figure out on it's own, you do not need to explain to the model how to use a cli. also if you eng can login to prod on aws with no control you have a big problem sir.
English

The current "MCP is dead discourse" is my current favorite example of the really annoying "simplicity" brainrot that's been plaguing tech for a while
On paper "just use a cli agents already know bash" sounds really good. It makes sense and is true, but it misses the bigger picture:
> how do they know about the commands + their shape?
> just put it in your agents md file or make a skill
> ok, so then what happens if the cli's shape changes
> well then u just update the markdown file
> fine let's pretend people will actually do that (they will not) and this actually works, how are you going to scope authentication and authorization?
> use the cli auth tools like what AWS has
> ok so we need eng's or agents to be manually making sure every project switches the auth to the correct scopes for each project so that prod can't get vibe killed and then to connect to our internal services over cli in cloud agents we need to run basic agents in sandboxes now b/c we're not using mcp and...
You get the point.
It sounds really simple, and it is in the toy case, but in the real world an external API gated through MCP is actually way simpler, more secure, and manageable in a lot of cases.
This post & article from @GergelyOrosz is a very good example: x.com/GergelyOrosz/s…
It's the same thing with the $5 VPS or htmx or postgres or whatever other "simple" enlightened solution that works great in dumb indie hacker demos while making zero sense in the real world. I hate to break it to you guys, but there's no conspiracy. If modern tech solutions really were over complex slop do u really think these companies wouldn't take the free win to just do it the "simple" way? There are tons of problems with the tech, but it exists for a reason.
I like CLIs a lot, and in a lot of cases skills make sense, clis make sense, etc. There are a lot of ways to do things, and they all solve different problems.
But no, MCP is not dead. It or something like it isn't going anywhere. And there are a lot of good new ideas of how to make it better!
Dumping an MCP with 60+ random tools into context sucks I completely agree and needs to be fixed. A lot of the code run solutions are very compelling like @RhysSullivan 's executor, cloudflare's code mode, and others. There are ways to fix this, but a "god mode bash tool" isn't it.
English

In a rational world, the harness is outside the sandbox. Security boundary, independent infra concerns, etc.
But the world isn’t rational and we should work with that.
Erik Dunteman@erikdunteman
Harness inside the sandbox, or outside the sandbox? Why?
English

we spoke to a company today who's security team is so concerned by ai code they're considering banning ai tools
your first reaction might be "they're gonna get left behind" but if you are practical their concerns aren't invalid
if you are a huge multi national org with tens of thousands of employees and they just got a button that appears to do their work, it's gonna get pushed a lot
and the process around knowing what is making it to production is totally melting
being honest we're all getting a bit lazier
see that kiro related aws outage as a real life example
so they're genuinely arguing over how much this is going to be allowed esp since the net productivity gains for the average dev seem to be pretty low
English

We were Clay's largest user at one point in time, hitting their platform 17.3 million times per week. Last month we replaced them entirely with a $200/mo Claude Code subscription.
I can't write code. Neither can James, my VP of Growth who built the replacement.
Here's the full story.
Clay is a GREAT product and I TRULY think most people should use it. But we hit their ceiling.
50,000 row limit per table.
12.5 million row cap per workspace.
Tables that take days to actually delete.
Clicking "run all" thousands of times and waiting days for things to clear out.
So
When you're processing millions of leads, all the above become the bottleneck of your entire business.
James had never touched Claude Code before. Three weeks after learning it, he built our entire core system.
With Clay, processing 1 million leads took 27 hours.
And it would error out often enough that we would always have to plan on hitting the “run all rows” button again on 20+ clay tables. IYKYK
but
Our new system waterfall enriches 1 million leads in 5 seconds. 272,000 leads PER SECOND.
AND On top of the core engine, we vibe coded a Google Maps scraper that pulls leads zip code by zip code across all 32,000 US zip codes.
AND An AI lead finder that hits 95% contact match rates where Apollo gives you about 30%.
AND Ad library scrapers for Google and LinkedIn.
AND An AI campaign analysis system.
AND An auto-refill system so clients never run out of leads mid-campaign.
One we started building with Claude, we just couldn’t stop
Now we have the data ready for clients sending 5 million emails a month within 1 week of signing the contract.
I put together the full system blueprint -- every tool, the tech stack, a Clay vs custom comparison, and a 6-step playbook for building your own. Plus a video walkthrough where I show you the live system and how each tool actually works.
Retweet or Reply CODE below and I'll DM it to you.
English

@NotionHQ And here's the case study: joinformal.com/customer-stori…
English

I'm a product-obsessed founder. Crafting a delightful product experience is my north star.
Few companies embody that level of craft like @NotionHQ — and today I'm incredibly proud to share with the world our latest case study.
@NotionHQ now secures 100s of datastores with Formal.
I’m deeply grateful to the Notion security team for betting on us when we were still an early-stage company. We’ve learned so much along the way, and working with them has truly made our product better.
@joinformal ❤️ @NotionHQ
English

