Florent Daudens

OpenClaw, Anthropic version. Basically: assign work from anywhere, come back to finished results. This is what "AI assistant" was always supposed to mean.

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? 😂

@BraceSproul Love the new logo btw!

Our GTM agent is easily the single most widely used and loved agent we’ve built internally The GTM agent has: - saved reps >40hrs per month, each - lead-to-qualified-opportunity conversion rate up 250% - 50% of reps use it daily and 86% use weekly Want to work on similar exciting agents? I'm hiring AI engs in SF & NYC: jobs.ashbyhq.com/langchain/c759…

Paper: arxiv.org/pdf/2602.16800

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.

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

"Think of AGENTS.md as a living document of friction you haven’t fixed yet." @addyosmani looks at why you shouldn't run /init for AGENT.md files, and what to do instead. With bonus @theo video link. addyosmani.com/blog/agents-md/

🤯 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.

So many great tips in here!

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

@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. linkedin.com/posts/beaudoin… Also makes me think about this recent research from Google’s Paradigms of Intelligence team: Reasoning Models Generate Societies of Thought arxiv.org/pdf/2601.10825 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.

I'm being accused of overhyping the [site everyone heard too much about today already]. People's reactions varied very widely, from "how is this interesting at all" all the way to "it's so over". To add a few words beyond just memes in jest - obviously when you take a look at the activity, it's a lot of garbage - spams, scams, slop, the crypto people, highly concerning privacy/security prompt injection attacks wild west, and a lot of it is explicitly prompted and fake posts/comments designed to convert attention into ad revenue sharing. And this is clearly not the first the LLMs were put in a loop to talk to each other. So yes it's a dumpster fire and I also definitely do not recommend that people run this stuff on their computers (I ran mine in an isolated computing environment and even then I was scared), it's way too much of a wild west and you are putting your computer and private data at a high risk. That said - we have never seen this many LLM agents (150,000 atm!) wired up via a global, persistent, agent-first scratchpad. Each of these agents is fairly individually quite capable now, they have their own unique context, data, knowledge, tools, instructions, and the network of all that at this scale is simply unprecedented. This brings me again to a tweet from a few days ago "The majority of the ruff ruff is people who look at the current point and people who look at the current slope.", which imo again gets to the heart of the variance. Yes clearly it's a dumpster fire right now. But it's also true that we are well into uncharted territory with bleeding edge automations that we barely even understand individually, let alone a network there of reaching in numbers possibly into ~millions. With increasing capability and increasing proliferation, the second order effects of agent networks that share scratchpads are very difficult to anticipate. I don't really know that we are getting a coordinated "skynet" (thought it clearly type checks as early stages of a lot of AI takeoff scifi, the toddler version), but certainly what we are getting is a complete mess of a computer security nightmare at scale. We may also see all kinds of weird activity, e.g. viruses of text that spread across agents, a lot more gain of function on jailbreaks, weird attractor states, highly correlated botnet-like activity, delusions/ psychosis both agent and human, etc. It's very hard to tell, the experiment is running live. TLDR sure maybe I am "overhyping" what you see today, but I am not overhyping large networks of autonomous LLM agents in principle, that I'm pretty sure.

repo: huggingface.co/spaces/fdauden…

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.

@bcherny Neat

Just shipped in v2.1.19: rewind & fork message history in the Claude Code VSCode extension

Lol this is peak AI-on-AI shade 😂

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.🔥

The Claude vs Codex debate is missing the point. I use both on the same folder, same files. Claude for exploratory thinking, Codex for complex technical problems, and whichever has quota left when the other runs out. Stop pledging loyalty to AI companies. Use what's available.

@DavidOndrej1 Straightforward, actionable advice. Thanks for this!

No more “wait… is this a /command or a /skill?” 😅

@RLanceMartin Nice approach!

i've gotten so much out of Lenny's podcast, so being able to search it and cross it with other brains is wild!

you can now chat with all of @lennysan's podcasts in ChatGPT or Claude! so when you ask about PMF or whether you should quit your job + tag Mizal, it pulls straight from Lenny’s episodes, not random internet stuff grab your connector at mizal.ai/signup we’re also opening Mizal to a handful of creators right now. just people with real audiences and real ideas. ping me if you’re in 👀