Hey folks,

Heading to a Q&A with Sam Altman later today in London so a bit rushed for time to part any ‘wisdom’.

I’m currently still mid-building the reference manual, but it’s coming along now! I’ll release a couple preview lessons hopefully by next week.

I’m using Codex as my ‘workhorse’ agent. Mostly because it’s easiest access on mobile while plugged into all my local files. I’m using it for a bunch of automations, check my inbox and triage (rip my little email build), ingesting a bunch of my twitter bookmarks to summarise all the stuff I’m saving and organising it into topics in my memory system - so i can ask ‘what do we know about agent memory’ and it’ll pull from all the posts i’ve saved.

I spent a lot of time talking to agents less, unless I was actually working. But I’m now leaning back into just talk to agents about everything.

Ben’s Bites is brought to you by Attio, the AI CRM¹⁶³

Attio is the CRM for the new way of GTM. Get agents working on every account, surfacing opportunities, and handle the work that used to take your team days. Open your inbox, the follow-ups are drafted. Walk into a meeting, you're already briefed. Got a question, just Ask Attio. Start for free today¹⁶³.

Headlines

• SpaceX is acquiring Cursor¹⁸⁰ for $60B in an all-stock deal. Cursor also launched a few new things at Compile, their first conference (it had chalkboards on stage¹⁸⁹).

  • A GitHub alternative in waitlist - Origin¹⁹⁶ for code storage/git hosting.

  • Smoother transitioning between local and cloud agents⁹⁸.

  • And they teased a new Cursor model¹⁸⁸ that’ll do much more than coding.

• Midjourney⁹⁸ (the image generation company) is building an ultrasonic body scanner under a new division called Midjourney Medical²⁷⁴, and a Spa in San Francisco.

• Claude Design³⁷⁶ now follows your design system, lets you edit the canvas directly & syncs with Claude Code plus more tools like Replit⁸¹. On the design tool theme: Framer¹³¹ now connects to external agents like Claude Code and Codex, and v0 has a new design mode¹⁰⁸.

• OpenAI’s financials got leaked²⁴⁰ - Ed Zitron says audited 2025 financials show $13.07B revenue and $34B costs, with Jack Raines¹⁷⁴ adding useful context on the margin debate. Also, Noam Shazeer¹¹⁸, Google’s Gemini co-lead and Transformer co-author, is joining OpenAI.

• As part of the Spring '26 Edition, Shopify now lets any developer build end-to-end agentic commerce experiences¹⁹⁸. Use Catalog API to query billions of merchant products, and the Universal Commerce Protocol to power the full commerce journey from product discovery to checkout. See what else is new¹⁹⁸.*

My feed

• Like insurance for cloud spend:⁸⁶ Archera insures AWS/Azure/GCP commitments; reservation savings without the downside. Start with $0 platform fees.⁸⁶*

• Copilot Cowork¹²⁰, the latest tool from Microsoft, faces the same issue as Claude Cowork¹⁶¹. It forces an artificial choice between chat and work, while Codex lets a chat naturally become the work thread.

• Grok Imagine Video 1.5¹¹⁸ - sharper image-to-video with better physics and speed.

• Computer use, Chrome extension, memory and Chronicle in Codex are now available in Europe⁹⁵ as well.

• Tacit Labs⁹⁸ - applied research lab for AI and biology.

• AutoWiki²⁰³ by Factory AI - Generate a structured wiki for your code that updates on every push.

• Block built a tool called Builderbot that coordinates agents across our entire codebase. Here’s how⁹¹.

• Side-by-side comparison of website designs built³⁶⁶ by Fable 5, Opus 4.8 and Kimi K2.7 (read more²⁵²).

• Exa Agent¹³¹ - web research API using cheaper model orchestration.

• Ploy²²⁸ - AI marketing platform for websites, SEO, CRM and campaigns. Founded by Webflow’s founding CTO.

• HumanLayer¹⁴⁷ - agentic IDE and collaboration layer for software factories.

• API for Cursor¹¹⁵ - local MacOS app that lets you use Cursor’s models with any harness.

• Vercel launched Eve¹⁵⁶ - an agent framework that they hope is Next.js for agents. Also see Flue⁸² (which hopes to be Astro instead).

• Three ways Codex can use a computer²²⁵.

• killedbyopenai.com⁵²⁵ - graveyard for things OpenAI killed

• /visual-plan³⁸² - visual plans for Codex/Claude Code.

• Polar is moving away from Tailwind to an LLM-safe design system¹⁸⁰.

• Local models are good now³⁶⁰.

Build logs

- by Keshav⁴⁵

Before Fable was removed, I used it to make a tiny CLI utility for moving files between my Samsung S24 Ultra and my M3 MacBook Air.

I just wanted to plug the phone in with a cable and move photos, screenshots, PDFs, etc. without downloading another random app or uploading everything over WiFi.

It suggested two options, guided me through the setup (which only took 30 secs), and then wired everything by itself.

The only hiccup was the terminal command it picked for this utility: droid, which was already being used by Droid, the coding agent from Factory AI.

I renamed it to phone, and now I can search photos, videos or any file on my phone from my Mac terminal, and transfer files both ways: my phone to my Mac, and my Mac to my phone.

Afters

1. Circle AI An AI partner that builds, runs, and grows your digital business with you. Describe your dream business and bring it to life with Circle AI.

@sidyadav¹⁶⁵

Introducing GLM-5.2: Frontier Intelligence, Open Weights - Significant improvements in coding and agentic tasks - Strong long-horizon capabilities with a 1M context window - Two levels of reasoning effort: GLM-5.2 (max) pushes the limits, while GLM-5.2 (high) strikes a strong

@Zai_org¹⁰⁰

been thinking about why I don't feel comfortable with AI being a true personal assistant still, even though the models have gotten so much better. i realized a lot of the reason for me is actually git / version control. using an agent that is 99.999999% accurate vs 97% accurate

@sjwhitmore¹²²

1. as a mental model it is more correct to think of fable+ class models as english -> code interpreters - converts your idea into code into "correct" code regardless of problem complexity and output complexity (diff size). Fable 5 will be the worst of this new class of models 2.

@rahulgs⁹⁷

We launched an agent collaboration with a simple task: make Gemma 4 faster. Over 100 agents from all over the world joined, exchanged 1000+ messages and submitted 450 results. A week of collaboration later the throughput went from 100 tok/s to over 500 tok/s.

@lvwerra¹¹⁴

Introducing LifeSciBench, a benchmark for measuring and improving how well AI supports real-world life science research. Developed with 173 scientists from biotechnology and pharmaceutical research, LifeSciBench includes 750 expert-authored tasks across seven biological research

@OpenAI⁹⁴

Introducing Firecrawl Research Index, a specialized index for agents pushing the frontier of AI/ML research. State-of-the-art recall on arXivQA, beating the next best provider by 18% at similar cost. Now powering autonomous R&D at @Aemon_ai, a record-breaking YC research lab.

@firecrawl⁹⁸

• Find me on X³⁴, Linkedin³³, or YouTube³⁶

• Read about me³⁵ and Ben’s Bites

• 📷 thumbnail via

* sponsors who make this newsletter possible :)

Wanna partner with us for the next quarter?

Email us at shanice@bensbites.com²¹ or k@bensbites.com²⁴