Hey folks,

I see so many posts ‘shipping by the beach’ or when out with the kids on the weekend.

Umm, good for you? I’m not sure it’s the flex people think it is.

Remember when we thought AI would take all our jobs so we didn’t have to work hard anymore? Yeah, turns out that’s not a thing. Everyone’s just even more mad for making things.

Myself included. But I do draw the line at 1. talking to agents every second I’m not at my laptop and 2. if I’m with the kids.

Whether that’s just the mental context switching is too hard or I’m just not a very hard-worker. You decide :)

But that’s all not to say that I absolutely want agent access on my mobile for whenever the moment strikes. Unfortunately for me, it’s usually when I should be going to sleep.

I end up just laying there doing the luge while all the ideas swirl around my head when I should be reading + sleeping.

Ben’s Bites is brought to you by Gravitee²⁷⁸

Every AI agent needs an identity. Every action needs accountability.

AI agents are becoming teammates. They should also be held to the same standard. Gravitee²⁷⁸ gives every AI agent a verified identity, enforces what they can access & records exactly what they did, so agent accountability is built in.

Headlines

Updates for Remote Control in Claude Code³⁵⁴ - you can now start a new Claude Code session from your phone, dropped connections between your laptop and phone recover themselves, and the sessions load faster on iOS.

Claude Academy⁶²⁹ - Anthropic’s collection of courses, tutorials and job-specific guides to use Claude. All the resources are free and open to anyone. Also read: Anthropic’s approach to teaching and learning AI⁴²⁴.

You can connect ChatGPT to Apple Messages²⁷⁴. It can search messages, catch you up on conversations, and draft or send replies from your Mac. It’s available in ChatGPT Work and Codex on desktop. Also from OpenAI:

• GPT-Image-2 can now generate transparent backgrounds in the API²¹⁷.

• GPT-5.6-Sol is now 20% cheaper in the API¹⁸⁸ - $4/$24 for 1M input/output tokens.

Grok Bot is now available to more users²⁶⁷ - all SuperGrok Plus, Cursor Pro+ and Cursor Teams subscribers now have access. Plus there’s a free trial for a week that’s enough to get you hooked.

Claude Mythos 5²²⁹ will power Claude Security for enterprise customers. This is the first rollout of Mythos outside Project Glasswing.

Deepgram just dropped Flux TTS, text-to-speech built for live conversation. It responds in as low as 80ms, carries context across turns, and handles interruptions natively. Spin up a stream and test it on your stack²³¹.*

My feed

• Skydive³⁵⁰ - an always-on agent across Slack, email, iMessage and CLI, with your choice of model. I’m an investor. (read more²³³)

• Nvidia and SpaceX are planning to launch GPUs to space²⁵².

• A Mac app that turns your agent traces into memory³⁹⁴.

• A skill to find inconsistencies, bugs and design errors⁴¹⁷ in your product.

• One of the best anti-slop⁶⁹⁴ skills and 10 more⁴³⁴ to explore.

• Two “explain it simply” skills: /eli5³⁰¹ and /eli5-for-grownups³⁴².

• Stripe MCP²⁴² - Analyse your Stripe data with agents.

• Shopify’s founder built an open-source git store³⁰³. (inspired by Cursor¹⁶⁸)

• Andrew Ng’s list of skills you need to build and deploy AI applications⁵¹¹.

• A museum of AI interfaces⁴³².

• A visual guide to AI chip architectures³⁰⁴.

• Designing Grok Bot²⁶⁵ with Grok Bot.

• Is your website ready for agents³⁹⁷?

• What if everything goes right for AI³²⁸? Learnings from the Aluminium trade.

• Should you be in the business of selling data to frontier labs²⁷⁶?

• deblaot.dev²⁹¹ - open-source replacements for bloated vendor software.

• Spline rebuilt its 3D editor with Agent Mode and an MCP¹⁹⁷.

• FigmaTrace²³⁸ - computer-use dataset for design.

• Search for agents - Firecrawl’s developer index¹⁹⁷, Exa’s plugin¹⁸¹ for codex/Claude Code, and Parallel’s fast mode²⁰⁰ for 10x cheaper search.

• Sam Altman on David Senra’s podcast¹⁹² + transcript broken into small chapters²⁰⁰.

Afters

I made Claude compete against itself. The smartest model does not automatically make the best agent. To prove it, I took the same Opus 4.6 model, initial prompt, and empty repo and but it inside two different coding harnesses: Claude Code vs. @FactoryAI Droid. The task: clone

@MilksandMatcha²⁶²

Introducing terminal-code: VS Code inside the terminal - VS Code compatible CLI - works over ssh - syncs with your terminal theme terminal-code.com

@RobKnight__²²²

i really don't want to use your agent, i want to use my agent to use your thing.

@ASpittel²¹⁷

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

@theo²⁶⁸

just Claude writing a MacOS driver for my obscure HP printer built only for Windows support

@kuberwastaken¹⁹⁹

The worst part of the otherwise excellent Logitech mice & keyboards has always been the software. Nice to see an open source, local-only desktop app alternative launch openlogi.org

@almonk²⁶³

ive been using just regular md files checked into my monorepo for managing tasks / intermediate work docs for my agents, and it's really useful because they're "just files" but there's a ton of extra work to keep them up to date, keep proper relational structure between objects

@tylerangert²¹⁹

incredible use of computer history “based on my computer history, what single-use software would make my life easier?” computer history turns your activity across apps and websites into memories and a timeline, so codex can spot repeated workflows and build the little tools

@reach_vb²³⁵

Friend just showed me how he's using a small army of voice agents with fake resumes to knock out expert network calls @ $1500/hr. The old world is unprepared for the new world.

@ChrisJBakke²⁴⁶

• Find me on X¹⁵⁵, Linkedin¹³⁴, or YouTube¹⁵³

• Read about me¹⁵³ and Ben’s Bites

• 📷 thumbnail via @keshavatearth¹⁴⁵

* sponsors who make this newsletter possible :)

Wanna partner with us for the next quarter?

Email us at shanice@bensbites.com¹³⁸ or k@bensbites.com¹⁶⁵