berni

[berni @bernirov]

Por si revisas mi tw, te extraño.

[berni @bernirov]

@liambraus feels less like a plugin system and more like the agent writing its own plugins whenever it wants

[ben. @benyuls]

estudiantes de marketing viendo esto

[ben. @benyuls]

in 2024 we asked AI to write our code

in 2026 we ask AI to rewrite itself

[marcus @marcusyul]

YOUR AI AGENT CAN NOW UPGRADE ITSELF.

Reef just launched /reefine:
you describe what you want and it builds the change, tests it and ships a new version on its own.

→ Adds new modes
→ Tells you out loud
→ Integrates new tools
→ Works with Codex, OpenCode...

Basically: your agent evolves just by talking to it.

It's open source. Link below :)

[berni @bernirov]

@marcusyul this is the real unlock. evals on every response instead of 5% sampling

[ares. 🎧 @aresotik]

GUÍA COMPLETA DE GROK BOT EN 13 MINUTOS

La explicación más clara que he visto.

Crea tareas.
Monta rutinas.
Personaliza tus propios agentes.

Grok Bot → Tareas → Rutinas → Agentes

🔖 Guárdalo antes de perderlo.

[berni @bernirov]

@benyuls esto ya no es una peli, es un videojuego sin mando

[berni @bernirov]

@mattknowsai good video man

[berni @bernirov]

@benyuls gm 🫠🫠

[berni @bernirov]

@marcusyul @vellum_ai finally an assistant that can actually see what im looking at

[Ali Ansari @aliansarinik]

Today we’re launching micro1’s PII transformation model, flow-transform 1.0, delivering frontier-level performance across detection, identity synthesis, and transformation of personally identifiable information.

On PrivacyBench, our model reaches 96.0% F1, outperforming every detection baseline we tested, including Tonic Textual, Claude Opus 4.8, Sonnet 4.6, Microsoft Presidio, Haiku 4.5 and GLiNER2.

Some of the most valuable training data for frontier AI models lives inside fully functioning companies. It captures years of real work across decisions, communications, tools, handoffs, exceptions and the relationships connecting them.

The problem is that this data is also full of PII.

Traditional redaction makes the data safe, but it also destroys the very workflows and relationships frontier models need to learn from.

flow-transform 1.0 solves this by turning enterprise operational data into high-fidelity training data for frontier models by replacing real-world identities without flattening the reality the data captures.

[berni @bernirov]

@benyuls tried it with my landing page and the competitor ads it pulled were scary accurate

[berni @bernirov]

@mattknowsai lo difícil no es montarlo, es decidir qué tareas delegar primero

[berni @bernirov]

@benyuls i was not expecting this today

[ben. @benyuls]

Epic Games CEO when he saw that an entire world can generate itself while you play and change based on what every player does

[berni @bernirov]

@nattcornelis love it

[berni @bernirov]

@dravenip Saving this before I even finish reading it

[berni @bernirov]

@marcusyul the postiz auto-schedule part is what sold me

[marcus @marcusyul]

ONE PERSON CAN NOW RUN A FULL CONTENT TEAM WITH GROK

One bot per job. You just make the calls.

→ Research competitors while you sleep
→ Pick the one idea worth testing
→ Build the assets with consistent avatars
→ Auto-schedule everything in Postiz

No camera. No editors. No team.

🔖 Save this.

https://t.co/0oyRrJaf9M

[berni @bernirov]

@benyuls goood