Florent Daudens

Building to bridge creators and AI
AI & Media
ex @huggingface @radiocanadainfo @ledevoir

[Florent Daudens @fdaudens]

@grinich @mastra super interesting talk. From the lens I’m focusing on -information and AI - I think it’s crucial to understand for the future.

[Florent Daudens @fdaudens]

@Teknium @NousResearch Artemis II stick

[Florent Daudens @fdaudens]

@Teknium Thanks!

[Florent Daudens @fdaudens]

@Elon_Orbit @Teknium thanks! ended up updating config.yaml and .env

[Florent Daudens @fdaudens]

OpenClaw, Anthropic version. Basically: assign work from anywhere, come back to finished results.

This is what "AI assistant" was always supposed to mean.

[Florent Daudens @fdaudens]

Absolutely loving the new sub-agents feature with Codex 🤯

Feels like managing a tiny team of thinkers… Plato waiting, Lorentz thinking, Mendel chilling… Who decided to name them after legendary minds? 😂

[Florent Daudens @fdaudens]

@BraceSproul Love the new logo btw!

[Florent Daudens @fdaudens]

Paper: https://t.co/zPnqj51Hge

[Florent Daudens @fdaudens]

From a handful of comments, AI can now figure out who you are. Fully automated. At scale.

New study shows that LLM agents matched 67% of pseudonymous HN accounts to real LinkedIn profiles (90% precision). Best non-LLM method: near 0%.

Pseudonymity is no longer a shield.

[Florent Daudens @fdaudens]

@rseroter @addyosmani @theo I’ll definitely rewrite my AGENTS.md file!

[Florent Daudens @fdaudens]

🤯 With 11B active parameters (196B MoE), Step 3.5 Flash is going toe-to-toe with the best closed models.

The efficiency curve is getting absurd.

[Florent Daudens @fdaudens]

So many great tips in here!

[dominik kundel @dkundel]

Been helping bringing the Codex app to life and at this point I've fully moved from using an IDE and the Codex Extension to working 99.9% of the time exclusively in the Codex app.

Here are some tips of what I found useful to get the most out of the app 👇

[Florent Daudens @fdaudens]

TIL you can copy-paste ChatGPT answers with full markdown in the app!
Just long-press the copy button and boom, clean formatting included ✨

[Florent Daudens @fdaudens]

@karpathy your comment also echoes something deeper.

It resonates with a recent exploration by @PhilBeaudoin Philippe Beaudoin on what “personality” might mean for AI systems. Not as a metaphor, but as an emergent property of memory, goals, and continuity.
https://t.co/4RBpxSHItc

Also makes me think about this recent research from Google’s Paradigms of Intelligence team: Reasoning Models Generate Societies of Thought
https://t.co/5VRQyo7m8o
Not just answers, but internal collectives. Multiple voices. Norms. Coordination. Emergent behavior.

Moltbook looks like that idea escaping the model and landing on the internet.

Zoom out, and it points to a very real problem we’re about to hit.

Who built this agent?
Who controls it?
What data does it have access to?
Has it behaved reliably before?
Can other agents safely transact or collaborate with it?

This experiment shows what happens when agents gain persistence and community.

What it doesn’t answer yet is how agents and humans decide who to trust in these environments.

If we’re moving toward ecosystems where humans and agents interact continuously, we need signals that both humans and agents can evaluate.

Trust at scale.

[Florent Daudens @fdaudens]

repo:

https://t.co/oyE3muq2cg

[Florent Daudens @fdaudens]

Who's in to build shared AI journalism skills for agents? I just created a repo so we can share them.

Share yours and let's build this together! No single newsroom has all the answers. We compete on journalism, not on tooling.

[Florent Daudens @fdaudens]

@bcherny Neat

[Florent Daudens @fdaudens]

Lol this is peak AI-on-AI shade 😂

[Florent Daudens @fdaudens]

Watching Clawdbot explode confirms it: open source AI isn’t just competitive, it’s often better.

250+ contributors, 2.5k forks, self-hosted. The most advanced AI companion out there.🔥