Hey folks,

I’m back from holiday and straight back to messing around building. I’ve been kinda obsessed and enamoured with the demos from tldraw. It’s a free canvas/whiteboard app but their offline app (recently updated⁴¹⁵) is cool because agents can do all sorts with it; create visualisations to explain stuff, make games, interactive blog posts and a ton of other stuff.

Like turning our logo into a little animating mascot. He’s called ‘bites’ btw.

or little widgets like a timezone checker

timezone checker in @tldraw offline

@bentossell²³⁵

or a daily weather timeline

ok obsessed with building little widgets in @tldraw

@bentossell²⁵¹

I’m not good using agents when everything is just text in a file. It’s boring, I don’t read it and I sure as shit don’t do enough (anything?) with it. So if it’s visual and all on one canvas, maybe I will?

My idea here is to create a little ‘one-stop’ canvas for some widgets I use regularly as well as showing me my todos/emails to sort and things like that. I’m then planning on making my personal site an interactive canvas too, then some more explainer-like stuff too.

And maybe I’ll get the mascot hooked up to an agent so i can drag him to my todos and ask him to do stuff…

I’ll share more soon 😊

Ben’s Bites is brought to you by Ability AI³⁴⁸

This startup runs on 17 AI agents¹⁹⁸ - and open-sourced the platform. Marketing, client health, competitive intel, finance - real ops, not demos, with every agent action git-tracked and a human approving anything external. Agents you own, not rent. Apache 2.0: github.com/Abilityai/trinity³⁴⁸

Headlines

Claude Opus 5 is out¹⁷⁶ - Anthropic says it gets close to Fable 5 at half the price. Claire hated using Opus 5, but when asked to rank model outputs in a blind test, she ended up rating it first³¹².

Every’s review¹⁸³ lists some behaviours that might explain this: it argues, stops early and fights the skills people built for older models.

And maybe we are overprompting it.

I spent multiple hours today hand writing better CLAUDE․md/AGENTS․md and half a dozen skills. Audited and deleted a similar amount. I'm sad to report it was 100% worth it.

@theo²³⁵

Anthropic says it removed more than 80% of Claude Code’s system prompt²⁰⁰ for Opus 5 and Fable 5 with no measurable coding-eval loss.

ChatGPT Voice can now run the ChatGPT desktop app¹⁸³. You can use it in ChatGPT Work and Codex both; just start a “Voice” session and speak to it. It can create new sessions for individual tasks and then report the results to you in the main thread. It feels a lot like OpenClaw with voice.

I didn’t have a great time using ChatGPT Voice for “serious” work. The delegation of tasks to new sessions via ChatGPT Voice doesn’t feel as smart as doing it in a chat with 5.6 Sol in Codex. Maybe it’s the lack of control on what models/thinking level is used for each new session.

I imagine Voice to work great for productivity type tasks, checking emails, creating draft replies, pull some info from a dashboard and create a chart etc.

For serious work, I still prefer using a speech to text app (currently using one I built — optionafk.com¹⁹⁶) and sending that to the agent of my choice with full control over model/thinking effort.

— Keshav

Also, I wouldn’t blame you if you missed it, but Claude also has a voice mode¹⁸⁸. Till now, it could only use Haiku, but now it can use Sonnet and Opus as well as call multiple tools like Gmail, Calendar and Slack mid-conversation. I don’t remember when I last used Claude’s chat option. It’s been Claude Code for a long time now.

Kimi K3’s weights¹³⁷ and technical report¹²⁹ are out. It’s already available in Droid at 50% off until 10 August²⁰⁴.

Following rumours that the US might ban companies from using Chinese open-weight models, NVIDIA’s CEO Jensen Huang made his first-ever post on X²¹³ - a long statement backing open-source AI. Over the weekend, everyone signed that statement¹³⁷ (OpenAI, Google, Microsoft and 150+ more) - except Anthropic.

Of course, that led to some backlash, and Anthropic did what it does: published an essay¹⁶⁴ to save face, saying it never pushed for an open-weights ban. The reaction to it is people calling Anthropic out on their hypocrisy — they are okay with open models as long as they are cute little 8b toys¹³⁰, but not if they are “big, dangerous models” (to Anthropic’s business).

@AnthropicAI "Only we are capable of determining what ideas are dangerous. Peasants." ~

@NachoQuixotic¹⁸⁰

Quick links

• FLUX 3²⁶³ - one model for image, video, audio and action prediction; video is in early access.

• Health in ChatGPT¹⁹¹ - US users can optionally connect Apple Health and supported medical records, then ask about changes in context.

• BackSearch¹⁸⁶ - search the web as it was on a particular date in the past. Right now, it only works for news in 2026.

• here.now Workspaces²¹⁹ - private team home for the sites, docs and dashboards your agents publish.

• Why software factories fail - part 1³¹⁹, part 2¹⁴⁵, part 3¹⁷⁰.

• open-git¹⁷² - a code host built for agents, with an autopilot that fixes your PR when CI goes red.

• OpenWorker²⁶⁸ - open-source Mac agent that finishes everyday work and asks before consequential actions.

• Pilot Protocol²⁵⁹ - a network of over 250,000 agents that you can use to gain distribution for your app. (I’m an investor)

• Notion as code¹⁹⁹ - define your whole workspace in TypeScript and deploy it through the API. (beta)

• The Stack v3¹³⁶ - open code dataset with about 5T filtered tokens across 770 languages.

• box²³² - full VM sandboxes for your agents at $0.00001 a second, with snapshots, SSH and a desktop.

• Mintlify¹⁹³ - turns resolved support tickets into proposed documentation fixes.

• Cognition acquired Interaction¹⁴⁷ - the team behind Poke joins the makers of Devin.

Skills section

• Interface Craft¹⁹⁷ - four new lessons on advanced animation, plus an updated DialKit skill for timelines. (tweet¹⁰⁸)

• /prototype²⁴¹ - asks your agent for several UI versions and saves the chosen one in a shareable URL. (example run¹⁸⁰)

• Transitions.dev²⁰⁷ - 33+ polished UI transitions as copyable CSS or React, or an installable agent skill. (tweet¹²²)

• sharechat¹⁴⁸ - share a Claude Code or Codex session as an unlisted link; no signup, no login to read it.

Afters

@PjoyAI @lakshyaag I thought the way to announce such a thing was not to change your bio but to post the 10 paragraph essay that i just shared with the team?

@karpathy²⁸⁷

I've already had to update the guide to which AI models to use that I wrote on Thursday to include Opus 5 and Codex's voice mode, both of which are significant & launched on Friday. Keeping up is challenging, even if you are following this stuff closely.

@emollick²⁹²

Claude Opus 5 one-shotted this game. EVERYTHING you see in this demo is custom code... not a single external asset was used. AI games are going to be amazing. (sound on)

@mattshumer_⁴²²

I was travelling yesterday and left my Mac plugged in at home, and mostly did work via ChatGPT’s mobile app (using their Remote feature for Codex) and really liked the experience.

@Keshavatearth¹⁴⁵

Capitalism is just so beautiful. $8 trillion worth of market cap coming out in support of open-weight models because it's good for their business and makes them look good... and, totally coincidentally, it also happens to be better for us consumers and practically every

@packyM¹⁶⁵

someone should invent a version of Gmail that can search your inbox and return the emails that match the term you're looking for

@james406¹⁷¹

• Find me on X¹⁰⁷, Linkedin⁹¹, or YouTube⁹⁷

• Read about me¹⁰² and Ben’s Bites

• 📷 thumbnail via @keshavatearth⁹⁷

* sponsors who make this newsletter possible :)

Wanna partner with us for the next quarter?

Email us at shanice@bensbites.com¹⁰² or k@bensbites.com¹¹²