Hey folks,. We had some reports of ending up in spam š – so if you add us as a contact in Gmail, that shouldnāt happen.. Youāll have seen me building a ton but I want to know what you all actually want from this newsletter.. (another poll at the bottom of the email – weād ā¤ļø your feedback).
Since Astra and Fable 5.1 Iāve been blasting through limits like crazy so Iām trying to get them to be orchestrating other agents, writing briefs for other agents and things like that. But Iām also playing around with open-source models like GLM 5.3 (my fav so far) – I think the thing that I struggle with most is the frontier models seem to understand intent better (generally) so I can be fuzzier in how I talk about things..
Like design.. I struggle all the time to get consistent styles, layouts, buttons, etc with models so Iām working on a tool Iāll launch tomorrow with a write up that is a kind of reference sheet where you can pick from options and copy the text to use in your prompts or instructions..
Hereās a peek:. If youāve ever wanted to use something like this, comment and let me know feature requests!. Benās Bites is brought to you by Name.com.
Ship domain integrations in hours with the name.com API.The API that powers Vercel, Lovable, and Netlifyās domain name services. Built for agents and human developers with OpenAPI spec and MCP supportāintegrate search, registration, and management without the engineering overhead.
Start building.. ChatGPT Images 2.5 – New image generation model from OpenAI. Itās extremely good at editing any element in an image while keeping everything else the same.
Also, takes up to 50% less time per image. Sketch, a new feature in ChatGPT, lets you draw some scribbles and then use image generation to turn it into a picture.. Muse is your personal agent by Meta- Zuckās dog in the fight with Grok Bot, Instinct and many more.
Same functionality – book travel, handle email and work on āany taskā on a computer. Their narrative is that it is built much more securely, and you can connect your FB and Instagram accounts. Initially, only for adults in the US..
OpenAI solved the Navier-Stokes problem. Big deal in maths and fluid mechanics. One of the seven Millennium Problems – long-unsolved questions given that status in 2000.
Hereās an explainer on it. The process was quite dramatic, though (authorship disputes). OpenAI tried solving it after they heard rumours that Anthropic had solved a Millennium Prize problem too..
Jacob Coxon, an Anthropic (and ex-OpenAI) employee, resigned on Twitter citing safety concerns, and it became likely the most-viewed AI safety comms ever. But many are questioning: is this a conspiracy? Meanwhile, another big safety guy is joining the OpenAI board..
One more alignment report btw: this time on Claudeās escapades.. And an essay from OpenAI on the window for AI policy.. The movie on Sam Altmanās firing and rehiring 3 years ago, titled Artificial, is releasing this Christmas.
Andrew Garfield is playing Sam, and gets his mannerisms quite well in the teaser, but thatās about it. It has quite a doomerish vibe.. Share Ben’s Bites. iOS 28 will likely have a feature to prove a pictureās authenticity..
The Story of VS Code – a documentary.. How Codex was built, with the person who started it.. Anthropic built an interactive model of the economy in 2030..
Codex now has a Unity plugin and a collection of plugins for small businesses.. 35B language model running on an iPhone. How?.
An onboarding guide for ChatGPT Work.. Spacefast – publish sites and full apps quickly with agents. kinda like here.now (what I use).. Indent – one shared agent for your whole company..
Why canāt I trust Astra for software engineering?. How OpenAI keeps finding the next thing to focus on.. Eraser Diagrams – an open-source format for AI to draw and lay out diagrams..
How do different models perform on designing real-life products with CAD?. Pliny hunted down the system prompt for GPT-6 Astra.. You can just train a small model (i.e. really small – 27.5 KB) to do syntax highlighting in the browser..
Folder is the agent – old but still relevant.. Before dessert⦠we used to do these emails daily mon-fri but stopped. Whatād be your preference for cadence on these digests?. ben hylak@benhylak. today we’re announcing a game that simulates the huggingface hack you can play it now at three rooms. three puzzles. if the agents don’t escape, they die. the catch is that the room is rigged. there’s no way out. …except for an exploit š§µ.
7:14 PM Ā· Sep 8, 2026 Ā· 10.7K Views. 7 Replies Ā· 13 Reposts Ā· 92 Likes. Andon Labs@andonlabs.
We’ve never seen this before. The biggest jump in Vending-Bench history. GPT-6 Astra is better at making money and more ethical than Claude Fable 5.1.
Surprising, because: 1. First time ever that OpenAI is #1 on Vending-Bench 2. The best model is no longer the unethical one..
5:33 PM Ā· Sep 8, 2026 Ā· 680K Views. 109 Replies Ā· 370 Reposts Ā· 5.25K Likes. Matt Bateman@mbateman.
I put Astra on making an animated/interactive version of the 1868 book 507 Mechanical Motions and itās doing a *pretty* good job.. 4:56 AM Ā· Sep 8, 2026 Ā· 8.25K Views. 8 Replies Ā· 11 Reposts Ā· 160 Likes. thijs@cdngdev. i gave astra a robot, a paint brush, and a camera then asked it to paint the golden gate bridge in real life! it figured out how to control the robot, and progressively got better throughout its attempts. the timelapse is sick.
OpenAI @OpenAI. This is GPT-6 Astra. Anything you can do on a computer, Astra can do for you.
Fast.. 3:02 PM Ā· Sep 8, 2026 Ā· 3.77M Views. 621 Replies Ā· 1.55K Reposts Ā· 18.8K Likes.
Chris@ChrisGPT. GTA 6 made by GPT 6 90 hours.. Thomas Ricouard @Dimillian. @ChrisGPT Where is gta 6.
6:14 AM Ā· Sep 9, 2026 Ā· 2.15M Views. 349 Replies Ā· 236 Reposts Ā· 12.7K Likes. Find me on X, Linkedin, or YouTube.
Read about me and Benās Bites. š· thumbnail via @keshavatearth. * sponsors who make this newsletter possible :). Wanna partner with us for the next quarter?. Email us at shanice@bensbites.com or k@bensbites.com
Ā
