Bookmarks
4039 items across 36 Twitter folders, Raindrop, and Readwise
Twitter Bookmarks
4039
https://t.co/4ldHxyh6KD
Over the last month I've been doing office visits with AI-native companies in San Francisco and weāve had the chance to actually see how they work today and we saw a lot that surpr...
The AI-pilled compounding startup
HOW TO GO VIRAL ON X: complete basics easy mode with first guest as @minmax0501 00:00 Intro 00:50 @getyourmomo 01:16 First guest intro 02:16 Warm up account 02:51 Tip 1: tag communities 04:19 Tip 2: tag famous accounts 05:06 Understanding X audience 06:00 Things that didnāt...
https://t.co/ZC8Qlftkqo
The past few weeks I have heard story after story that has confirmed my suspicion: companies are setting a completely new standard for product velocity and ambition. If you're an e...
Yes, they're moving faster than you
https://t.co/EvpBN6owh5
Ramp published a post about Glass, the internal AI productivity suite they built for every employee. It's impressive work: auto-configured integrations, reusable skills, persistent...
How to Make a Company AI-Native (without building anything)
Screenshot of ChatGPT in 2028 images v2 https://t.co/1avxDqZXDK
https://t.co/aZnKZ1SVXB
Agent harnesses are becoming the dominant way to build agents, and they are not going anywhere. These harnesses are intimately tied to agent memory. If you used a closed harness - ...
Your harness, your memory
https://t.co/EVPCod6rxu
Steve Yegge says people using AI coding agents are "10x to 100x as productive as engineers using Cursor and chat today, and roughly 1000x as productive as Googlers were back in 200...
Thin Harness, Fat Skills
https://t.co/7kFjxY5i79
Codex is great at using tools when the tool can be expressed as a precise command. That sounds obvious, but it changes how I think about giving Codex access to things I use every d...
The best tools I give Codex are bespoke CLIs
https://t.co/1gEFc0KoMN
Multi-agent systems have shown promise in coordination, complex reasoning, and parallel workflows. However, they are often highly token inefficient. In hierarchical architectures, ...
Latent Briefing: Efficient Memory Sharing for Multi-Agent Systems via KV Cache Compaction
https://t.co/4AHzhcBlTY
Youāve spent the last year or so supercharging your life with ChatGPT and your Claude Max subscription. It feels pretty good, right? Research is faster; you no longer need to draft...
What Hermes Agent Can Do for You (And Why It Matters)