Hi folks,
I’ve not been building as much this week 😬 - hand, foot and mouth is back in our house (happens yearly with 3 young kids!), and I have to get prep done for my Stanford talk on the 28th - they invited me back!
I’ll be in SF that week, heading to OpenAI Dev Day on the 29th to see what goodies they have in store for us - I predict we’ll see some stuff today, and they’re bound to have a personal agent up their sleeves to release very soon (pure speculation though).
For my Stanford talk, I’ve actually gone back to revisit the reference manual/course I was making for months (and hated every version I made). But now, since doing my Friday posts, I feel like I’ve got a better feel for how to do the course. This time I’ve actually made lessons I’m happy with, which is already miles better than my last attempts.
I’ll try and whip up something for a post tomorrow, but we’ll see if time (and kids) permits.
Ben’s Bites is brought to you by Name.com124
Ship domain integrations in hours with the name.com API124. The API that powers Vercel, Lovable, and Netlify’s domain name services. Built for agents and human developers with OpenAPI spec and MCP support—integrate search, registration, and management without the engineering overhead. Start building124.
Claude Cowork is merging with Claude Chat319. No more separate tab for bigger tasks. All your connected apps, skills and context are available in a normal Claude.ai chat. It can also keep working after you close your laptop. OpenAI will likely follow this pattern soon and merge ChatGPT and ChatGPT Work.
Claude Artifacts is also getting dedicated products for Docs and Slides243, with Claude Design moving into conversations too. Is Anthropic invading G Suite and Office?143
Update on Claude Code’s latest experiment154. It has a name → Claude Mods434. Mods change how Claude Code itself looks and behaves. You can ask Claude to write these mods for you, so the app can fit how you work (well, Claude works and you play Tetris149).
Gemini API has two new Live models: 3.8 Live and 3.8 Live Extended Thinking126. These models take video and audio as input and output audio. They work great for use cases where you want the model to provide real-time assistance. I tried them in AI Studio for a couple of minutes, and didn’t notice any hiccups. It can be a great alternative to GPT-Live 1, since 3.8 Live is 7x cheaper.
New LLM killer model - Jev387. Built by TypeSafe AI. The founder co-created ChatGPT. Jev doesn’t really generate text like LLMs. Instead, it creates probabilities for possible answers. Suitable for software that needs lots of quick judgments111: what API to call next, which model to route a request to107, or a trading bot128. 5x cheaper inputs vs 5.6 Luna; free output tokens and 5.6 Terra-like performance on relevant tasks.
Union Alpha - new stealth model available through OpenRouter, Cloudflare89 and other providers. Outperforms 5.6 Sol71 on the DeepSWE benchmark at 5.6 Luna’s cost. Some rumours say it is a router; others say a GPT-6 variant (GPT-6 Luna??) or another GLM model (GLM-5.3-Flash launched this way). I had a good first chat with it; it spoke well, but then it revealed all my api keys in another session, and I’ve been getting ‘provider errors’ because it’s overloaded ever since….
Meta One150 - new subscription from Meta with extra AI features/usage in Muse and paid tools across Instagram, Facebook & WhatsApp.
Factory raised $200M at a $5B valuation171. To celebrate, I updated my plugin81 for using Droid in the bb app103. If I have to build anything ‘properly’ ie I care that it’s not vibe-slopped, I use Droid. And I’ve been using the Droid Core models a lot recently (open-source models) - they’re so quick, and not noticeably different from frontier models for most cases.
Inside OpenAI’s agentic software factory630.
Can AI models build a T-shirt store696? This was a cool read; also check out all the supporting docs she includes in the post.
Reception309 by ElevenLabs - an AI receptionist for small businesses.
How OpenAI plans to report models misbehaving105.
Slack Code145 lets your team and coding agents plan, build and review together
Pion230 - agents for running fully autonomous companies.
Which models are best at searching the web?276
Buzz181 - Your coding agent can ping your iPhone when it needs you.
Arrow 2 by Quiver161 - New SVG generation model. Their last one was way ahead of LLMs; curious how it compares with Astra now.
Code contracts181 - write down what your code must do, then have agents check it.
Self-updating docs163 from Mintlify. Now with ready-made automations.
An API to invent a dataset139 to train your models. (docs58)
TanStack Markdown134 - a tiny parser for docs, blogs and streaming AI responses.
Building a company brain491 people actually want to use.
A benchmark to answer how often AI agents cheat115.
Xiaomi’s AI team is streaming the RL run103 for their upcoming model.
What stays expensive when AI gets cheap463?
I made a website with 25 mini rooms, each with Claude keeping people company. Created with Claude Opus 5.
@kevin_t_ngo219
A quick EU founder survey: eusurvey.vercel.app.
@patrickc111
After one week, there are 5 more small models for specific tasks on the web: 1. gpu-time: natural language to JS date and time by @imarikchakma 2. gpu-query: natural language to structured filters by @cheatyyyy 3. neural-flexbox: model to centre a div (!) by @aaronvanston 4.…
@shuding104
okay i made a quick skill to get the model to delete useless UI copy. surprisingly works quite well with opus. have fun! paste.rachel.systems/ukogokijaz.md
the independence of AI evaluators is going to matter more... so i made it a "benchmark": evaluatorbench.com (research preview) source-linked directory of third-party evaluators of frontier AI. each one has an independence score you can take apart: change the weights, …
Read about me44 and Ben’s Bites
📷 thumbnail via @keshavatearth167
* sponsors who make this newsletter possible :)
Wanna partner with us for the next quarter?
Email us at shanice@bensbites.com175 or k@bensbites.com34
New home for Cowork
the successor of LLMs
2,829 readers clicked at least once. 49 links, 49 with clicks. Heat is relative to the most clicked link in this issue.
Substack · essay