Valentin

🏴‍☠️ – building mcpresso (turn your API into a compliant MCP server ready to deploy) and granular software (sandboxes for creating safe and powerful AI agents)

[Valentin @VLemort]

AI agents are not workflows or chatbots. They should improve over time, produce good surprises, and never break anything.

We are building sandboxes where agents can act, learn, and collaborate with humans, but only within limits defined by the developer.

https://t.co/uBjqJmrkJk

[Valentin @VLemort]

@RCLens La condescendance des supporters parisiens est insupportable.

Ils se disent grand club mais contournent le calendrier dès que ça les arrange.

Les vrais grands clubs (Real, Bayern…) assument, ils ne demandent pas de passe-droits.

[Valentin @VLemort]

@paulg The problem isn’t OpenClaw.

The problem is giving probabilistic systems tools and letting them act in the real world.

Noise is inevitable.

[Valentin @VLemort]

Less is more.
Never been more true.

When producing 1,000 words takes 30 seconds,
the scarce thing is not content.

It’s clarity.

Content abundance creates attention scarcity.

[Valentin @VLemort]

SaaS is dead’ is an intellectually lazy take.
Historically, very few models die. They mutate. What’s under pressure isn’t SaaS, but SaaS that sells potential instead of outcomes. Declaring a death is easy. Building what comes next is the work.

[Valentin @VLemort]

@BenjaminDEKR Data and inertia

[Valentin @VLemort]

@levie Great piece. One addition:

Context only compounds if agents can build on previous work. Most reset between sessions.

https://t.co/rFMzcdoBzg gives agents runtime environments where their work persists and builds on itself.

[Valentin @VLemort]

@StBelkins @ivanburazin The hard part is the safely part.

And “OS” here doesn’t mean a classical, human-designed OS, but one designed for AI.

Giving LLMs access to regular computers hasn’t produced truly autonomous agents, because human OSes lack the right primitives.

[Valentin @VLemort]

@zby Spent most of 2025 on this.
The issue is that sandboxing solves containment, not agency.
The real primitive feels closer to a runtime and a programmable environment for agents.

[Valentin @VLemort]

@lukestanley I agree. Prompt chaining and agentic harnesses aren’t the missing piece.

Even with MCP, adaptability doesn’t magically emerge.

You need a programmable runtime environment the agent can reason about and act within.

That’s the layer I’m working on. Still early, but promising.

[Valentin @VLemort]

@hnshah @mpanzz

[Valentin @VLemort]

@Austen Fully agree, when average quality collapses, anything genuinely good becomes disproportionately valuable.

[Valentin @VLemort]

If OpenAI announces something like that, the market will probably hit Google and Meta’s stock immediately, which forces them to shift focus whether they want to or not.

Reacting, they'll might create more openings.

[Valentin @VLemort]

@OpenAI why chase model leaderboards

when you could drop the first AI-native ad platform?
Integrated inside ChatGPT.

Priced per sale, not per click.

A product Google and Meta can't copy without breaking their revenue model.

One move.
Full market shift.

[Valentin @VLemort]

@kwharrison13 Make no money’ is meaningless.
Amazon didn’t ‘make money’ for a decade, OpenAI neither.
What mattered was cash flow growth and market capture.
Profit isn’t the lens you use for venture

[Valentin @VLemort]

@ThomasSowell Friedman is right.
But today the issue is different.
Most Western politics are purely reactive and in that environment, measuring “results” barely means anything.

[Valentin @VLemort]

@kevg1412 If you’d posted that same line as “Bob Doe”, it would have done 10 views.
Same idea, same quality, zero reach.
We don’t reward insight, we reward signatures and it’s absurd.
.

[Valentin @VLemort]

@paulg @mattyglesias Agree, a large part of today’s ‘AI revenues’ is still investor money going in circles: VC → LLM APIs → burned compute → customers paying only a fraction of the real cost.

[Valentin @VLemort]

@omarsar0 @mpanzz

[Valentin @VLemort]

@elonmusk True only if people actually have the tools, the time, and the desire to think.
Most of the time, they just react emotionally and call it an opinion.