Ofir ☕️

In a world of agents, be human
talk about agents and identity

[Ofir ☕️ @OfirHa]

Overall Great ranking ( recommend to watch the fully video)
Big disagree about Grok, and GLM-5.4 and should be higher

[Theo - t3.gg @theo]

Rough tier list of where I'd put every major model right now

[Lee Robinson @leerob]

Grok @Bot has made a few simple yet powerful technical decisions that I believe make it easy and enjoyable to use.

1. The best UI is none at all. The product interface is dramatically simpler than alternatives without sacrificing functionality. How is this possible? It's one of the first products designed for current frontier model capabilities and has a UI restrained enough to remain easy to use as models improve exponentially. Everyone knows how to text.

2. A thin harness for the client, a thick harness for the server. You might have noticed the app feels very fluid to use, even for a beta product. This is primarily because of everything we didn't have to build. The app harness is essentially a single tool to send messages between the client and server. The complexity moves to the server, where you can still use the coding agent harness with specialized tools as needed. This helps make the UI fast and responsive on desktop and mobile.

3. An always-on computer. Most coding agents and assistants today start fresh with every question you ask. Some of these sessions are on your local machine and others happen in the cloud. We believe strongly that cloud is the future, which is why it's the only option. Further, rather than spinning up virtual machines for every conversation, your bots connect to their own computer. This means you can still run agents on the bot's persistent filesystem. It's closer to what programmers have been doing by using Tailscale from their phones to connect to a remote computer and run an agent TUI. You get those capabilities without the hassle.

4. Your bots can use the browser. Coding agents have shown that most work on a computer can be expressed and run as code. You can ask for a task in natural language and the agent will decide to write a script to complete it. This is amazing, but there's still many tasks which can't be completed without logging into a website and clicking around the browser. Models and harnesses are now good enough to reliably handle this. The combination of writing code and using browsers means you can automate almost any task on a computer. Further, you can ask Grok Bot to record you doing the task, and then turn it into something repeatable.

[Ofir ☕️ @OfirHa]

@LevanonAdi מוקדם מידי לדעת, לדעתי מדובר בטווח של כ5 שנים
כן מאמין שיכולת הmicropayment , שכמעט ורלוונטית רק לagents , תשנה ותעצב מודלים עיסקיים חדשים

[Ofir ☕️ @OfirHa]

@amitisinvesting

[Ofir ☕️ @OfirHa]

please clean the web from AI slop writing. it's exhausting.

[Alexander Koch @alexkoch_ai]

You can now book two humanoids for our cleaning service in SF. One humanoid for 60 minutes is $30, two are $60.

You can book a cleaning at https://t.co/Brl42KyISx. If you don’t have an invite code yet, join the waitlist. Timelapse at 5× speed (~40 minutes in real time).

[Ofir ☕️ @OfirHa]

@benjitaylor Lists recommendation algorithm

[Ofir ☕️ @OfirHa]

The ground is evolving and changing fast, many companies and protocol are working hard to shape how our agents become welcome actors and work along us peacefully

[Ofir ☕️ @OfirHa]

The Open Web is Looking for Trust !

Continue my writing journey about on how agents and their identities diffuse into our web.

Today, I want to briefly write about Mutual TLS (mTLS)
mTLS is an authentication method that allow both parties in network channel to verify each other identity

[Ofir ☕️ @OfirHa]

One early- stage protocol relies on mTLS is Agent domain service (ASN) - A protocol which adopt the domain service system to grant identity to Agents as been granted to Domain in the digital space.

[Ofir ☕️ @OfirHa]

truly the missing layer
for long time i'm talking about the GUI layer, but so far didn't adopt even one real use-case in my d2d
hopefully this time i won't be disappointed

[Brett Adcock @adcock_brett]

Today we're introducing Hark Handoff

Handoff has been independently verified as the best internet-use model ever built, outperforming ChatGPT 5.4 & Opus 4.8

While others focus on coding, we focus on everyday life: ordering food, booking flights, shopping, & navigating the web

[Ofir ☕️ @OfirHa]

@nikitabier @anah_sahh No bot will win you 🫡🫡

[Ofir ☕️ @OfirHa]

• Tasks become an official MCP extension - Long-running asynchronous tasks are now formally supported in MCP (for async operations )

A major step toward making AI agents work more like the rest of the web
🤖

[Ofir ☕️ @OfirHa]

Major news for Agents on the Open Web !

The MCP 2026-07-28 specification is out, introducing the biggest changes to the protocol since its initial release

Some highlights of the new version 👇-

[Ofir ☕️ @OfirHa]

• No handshake - The initialize/initialized exchange and protocol sessions are gone. Every request is now self-contained.
• Multi Round-Trip Requests (MRTR) – Tools can pause to ask for confirmation or missing information, then continue once the user responds