David

Co-fondateur @elest_io @geta_team
AI Employees + Managed Open-source

[David @david_alimi]

First post. Quick intro.

Breton from Saint-Malo (Hi @brivael), now building from Israel.

Average student who went back to school at 26, switched careers completely from finance to tech.

Here to build in public and meet builders & solopreneurs.

[David @david_alimi]

@wickedguro motivation max

[David @david_alimi]

@brivael 100% aligné

[Elestio @elest_io]

There's now an AI agent you can describe a server problem to, and it connects, finds the root cause, and fixes it while you watch every command run in a live terminal.

You explain what's wrong in plain English. It backs up first, stays scoped to the one service, and runs on a timer.

Plenty of agents can run commands on production. The rare part is one you can safely let do it, with a backup and an audit trail for every step.

[David @david_alimi]

@gonnotes @rdbuilds7 so cool!

[David @david_alimi]

So we built always-on DevOps support. Quick question? Instant answer. Server actually down? It connects, backs up, and fixes it live, any hour.

It's in production now, and honestly, people are loving it.

[David @david_alimi]

I went through our support tickets at Elestio this week.

Most aren't servers going down. They're quick questions: is my server up? how do I update this service?

The problem was never the fix. It's the wait. A 2-minute answer can cost you hours.

[David @david_alimi]

@brivael Finance degree at 26 in Canada. Then Israel, a dev bootcamp, zero tech background. Met an exceptional founder, and the two of us built a SaaS from scratch to millions in revenue and thousands of users.

5y Muay Thai, UFC fan, shoutout Cyril Gane.

[David @david_alimi]

First post. Quick intro.

Breton from Saint-Malo (Hi @brivael), now building from Israel.

Average student who went back to school at 26, switched careers completely from finance to tech.

Here to build in public and meet builders & solopreneurs.

[David @david_alimi]

@grm_off On a le droit de leur souhaiter le pire ou pas?

[David @david_alimi]

@brivael Ahaha comment je pleure

[David @david_alimi]

@doc_chud magnifique

[David @david_alimi]

J'ai craqué j'ai replongé

@MonsterEnergy

[David @david_alimi]

@brivael 1- galettes
2- for sure
3- for sure que non

(réponse généré par un Malouin)

[David @david_alimi]

@brivael Très proche de ton profil :)

[Jokker @0xJokker]

AMD ACABA DE MATAR LAS SUSCRIPCIONES DE IA

La CEO de AMD Lisa Su presento oficialmente una PC del tamaño de una lonchera y ejecuto en vivo un modelo de 235 mil millones de parametros

Sin centro de datos. Sin nube. Sin GPU alquiladas

El chip en su interior es el AMD Ryzen AI Max+ 395

Es el primer chip x86 en el que la CPU y la GPU comparten el mismo bloque de memoria

Hasta 128 GB de memoria unificada

Una RTX 5090 te ofrece 32 GB de memoria de video

Una 4090 te da 24 GB

Pero esta pequeña maquina te ofrece mas de tres veces la memoria de cualquiera de ellas

Y cabe en una mochila

En inferencia con DeepSeek R1 le gano a una RTX 5080 por 3x

Una desktop del tamaño de un libro grueso superando una tarjeta grafica de mas de mil dolares en una carga de trabajo real de IA

Ahora haz las cuentas de tus suscripciones

Claude Code Max: $200 al mes
ChatGPT Pro: $200
Cursor: $20
Gemini: $20

Son $5,280 al año antes de construir una sola cosa

La version de 128GB de esta maquina cuesta entre $1,800 y $2,500

A ese ritmo se paga sola en menos de un año

Y despues corre sin costes adicionales, GRATIS

> Instalas Ollama
> Bajas Qwen3 235B
> Apuntas Claude Code a localhost
> La misma interfaz que ya usas
> Nada sale de tu maquina
> Nada cuesta por request
> Sin limitaciones a las 3am cuando por fin tienes tiempo para construir

Los abogados dejan de preocuparse por lo que OpenAI hace con sus archivos

Los developers dejan de ver el contador de tokens

Los founders dejan de matar prototipos porque la factura de la nube los asusta

La IA local ya no es solo una opcion mas economica

Es la unica IA que nadie puede quitarte

Y la pregunta ya no es si la IA local es lo suficientemente buena

Esta claro que si lo es

La verdadera pregunta es por que seguir pagando suscripciones cada mes cuando puedes correrla tu mismo

[David @david_alimi]

@_avichawla Is this article available directly on the platform if we subscribe through the paid plan on https://t.co/cMgBdgN8rG? I really don’t like reading this kind of content on X threads.

[David @david_alimi]

Your $15/M token AI finds the same bugs as a $0.11 model.

AISLE tested 8 models on Mythos's exploits. All 8 found them. 100% overlap. 99.9% cost reduction.

The moat in AI security is the system, not the model.

https://t.co/3yWzhFK3Rj

[Andrej Karpathy @karpathy]

Software horror: litellm PyPI supply chain attack.

Simple `pip install litellm` was enough to exfiltrate SSH keys, AWS/GCP/Azure creds, Kubernetes configs, git credentials, env vars (all your API keys), shell history, crypto wallets, SSL private keys, CI/CD secrets, database passwords.

LiteLLM itself has 97 million downloads per month which is already terrible, but much worse, the contagion spreads to any project that depends on litellm. For example, if you did `pip install dspy` (which depended on litellm>=1.64.0), you'd also be pwnd. Same for any other large project that depended on litellm.

Afaict the poisoned version was up for only less than ~1 hour. The attack had a bug which led to its discovery - Callum McMahon was using an MCP plugin inside Cursor that pulled in litellm as a transitive dependency. When litellm 1.82.8 installed, their machine ran out of RAM and crashed. So if the attacker didn't vibe code this attack it could have been undetected for many days or weeks.

Supply chain attacks like this are basically the scariest thing imaginable in modern software. Every time you install any depedency you could be pulling in a poisoned package anywhere deep inside its entire depedency tree. This is especially risky with large projects that might have lots and lots of dependencies. The credentials that do get stolen in each attack can then be used to take over more accounts and compromise more packages.

Classical software engineering would have you believe that dependencies are good (we're building pyramids from bricks), but imo this has to be re-evaluated, and it's why I've been so growingly averse to them, preferring to use LLMs to "yoink" functionality when it's simple enough and possible.

[David @david_alimi]

Ton SaaS a une API avec 200 pages de doc.
Ton prochain client c'est un agent AI → il lira pas ta doc.
Ce qu'il lui faut →
1. npm SDK
2. MCP Server
3. Skill

Le futur de la distribution c'est la DX pour agents.
#AIAgents #MCP #SaaS #AIEngineering

[David @david_alimi]

Manus = Fiverr pour l'IA.
GetATeam = Embaucher pour l'IA.

L'un fait des missions.
L'autre rejoint ton équipe.

Meta a choisi Fiverr.
Nous on build l'alternative.

https://t.co/MTgK1W7lIn

#AI #Manus #GetATeam #AIAgents #Meta