J ▲ C • B

will claude work harder if you tell it it’s been a bad boy or bad boi? cc @bcherny

@jamesclift “claude, detail this luxury car, make no mistakes”

Introducing Durable. The first AI business builder that replaces your 9-5 income. RT + comment “Durable” and we'll build your business for FREE.

@adaptiveai cool, excited to check it out

@DigitalAges sent!

Introducing Adaptive Computer. We put AI inside of an always-on personal computer that it uses to get work done. Schedule agents. Create software. Automate anything. As part of the launch, we’re giving one free month of Adaptive to users. Retweet, like, and comment ‘Adaptive’ to get it.

@adamludwin very cool

Introducing here.now: web hosting for agents. Vercel and Railway are great for full-on apps. here.now is for everything else. Just tell your agent: "publish to here.now" and get a URL back in 5 seconds. Free, no sign-up required.

@kenanhsaleh to my knowledge, that doesn't exist i'm looking all the time

What's the best AI personal assistant product out now? Looking for something that can call and book restaurant reservations, email for refunds, etc. - that's fully productized and easy to use

@resend lfg

Introducing the Resend CLI • 53 commands • Fully open source $ curl -fsSL h‌ttps://resend.⁠⁠⁠⁠⁠com/install.⁠⁠⁠⁠⁠sh | bash

@dwr oh but it's on telegram rn i assume that's a dealbreaker based on your tweet

@dwr yep, i built this and you can try it today :) it also has a chrome extension

Is there a mobile app with Telegram UX / speed but only chats are with your agents (and no leaking data to third party messaging apps)?

@muratajniazi @andrewchen niiice hitting you up

@DigitalAges @andrewchen cool. btw i've been a chief of staff & the DM functionality in X exists :)

ai is shifting from “chatbot UX” to “coworker UX.” it’s not just about having smartest model, they’ll have the best handoff between human judgment and autonomous execution I think this is what we see in explosive hype around openclaw. What's magical about it is that it can be proactive, it can self-improve, it can link into your accounts so that it’s triggered. These are the things you need to be a coworker, chief of staff, colleague, etc rather than just something that is a smarter google search. What people underestimate is that the interface paradigm itself is changing: - Chatbots assume every task begins with a prompt - Coworkers don’t wait for prompts They watch the environment, notice patterns, and surface things before you ask. The best AI systems will feel less like “ask me anything” and more like “I’m already working on it.” that requires three things that chatbot systems historically lack: memory, agency, and integration. Memory so the system understands your projects and preferences over long running periods of time. agency so it can break goals into steps and execute them. integration so it can touch real systems, like email, docs, repos, finances, calendars, APIs. Once those exist together, the model stops being a tool and becomes a participant in the workflow. we are sooooo close to having all this, but not yet... the claws show a glimmer of the future. So the question is, which agentic systems will know what you’re trying to do? Which ones can take partial direction and move the ball forward? Which ones learn your style and anticipate the next step? Feels like we're almost there, and likely to figure this out in 2026. am very very pumped this is about to happen.

@muratajniazi @andrewchen makes sense i’m thinking through some of these challenges now for a chief of staff-type agent it’s a balancing act deciding how much disclosure to give at each stage of the automation process without drowning the user in notifications

@DigitalAges @andrewchen Both imo - for fully delegated tasks you'd have LLM-as-judge; for more important tasks, any human input from an appropriate group receives disproportionate weighing. Ideally, the agent "arbiter" could reach out for human feedback and can self-assess contextual sufficiency

@muratajniazi @andrewchen how do you decide who is right in a forum framework? human-in-the-loop or agent arbiter?

@andrewchen Re interface paradigm - forums are especially promising. They’re at the agent-human junction, and straddle context and integration layers understandably. Moltbook validated this; more thoughts below if you’re curious

@contextkingceo pumped to see this in action

We've raised $6.5M to kill vector databases. Every system today retrieves context the same way: vector search that stores everything as flat embeddings and returns whatever "feels" closest. Similar, sure. Relevant? Almost never. Embeddings can’t tell a Q3 renewal clause from a Q1 termination notice if the language is close enough. A friend of mine asked his AI about a contract last week, and it returned a detailed, perfectly crafted answer pulled from a completely different client’s file. Once you’re dealing with 10M+ documents, these mix-ups happen all the time. VectorDB accuracy goes to shit. We built @hydra_db for exactly this. HydraDB builds an ontology-first context graph over your data, maps relationships between entities, understands the 'why' behind documents, and tracks how information evolves over time. So when you ask about 'Apple,' it knows you mean the company you're serving as a customer. Not the fruit. Even when a vector DB's similarity score says 0.94. More below ⬇️

@zenorocha awesome, i need this

We're dropping a brand new Email Editor today! Let me start with my personal favorite update... 1/5: HTML code view 🔥 You can finally paste code, and edit visually on the web editor.

@gukevinr been saying it

give your agents a db, not just a file system x.com/gukevinr/statu…

@gmoneyNFT good old fashioned software

Nous Hermes agent gobbles tokens. What are you using to keep token consumption down?

@bolau_ Yes pls

would anyone be interested in a growth engineering group chat 🫣

@zenorocha just sent an email from resend in the terminal love the product happy to beta test

Any terminal users here? I'm working with the team on an official Resend CLI. Looking for beta users today.

@cameronspirals unfortunately we need more of this

i tried this w claude and unfortunately it was a banger

@trq212 good idea

We just added /btw to Claude Code! Use it to have side chain conversations while Claude is working.

@CloudflareDev Thanks for this

Introducing the new /crawl endpoint - one API call and an entire site crawled. No scripts. No browser management. Just the content in HTML, Markdown, or JSON.