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.com54
Ship domain integrations in hours with the name.com API54. 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 building54.
Claude Cowork is merging with Claude Chat228. 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 Slides172, with Claude Design moving into conversations too. Is Anthropic invading G Suite and Office?74
Update on Claude Code’s latest experiment84. It has a name → Claude Mods367. 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 Tetris87).
Gemini API has two new Live models: 3.8 Live and 3.8 Live Extended Thinking57. 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 - Jev309. 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 judgments52: what API to call next, which model to route a request to51, or a trading bot75. 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, Cloudflare24 and other providers. Outperforms 5.6 Sol21 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 One83 - new subscription from Meta with extra AI features/usage in Muse and paid tools across Instagram, Facebook & WhatsApp.
Factory raised $200M at a $5B valuation100. To celebrate, I updated my plugin38 for using Droid in the bb app59. 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 factory348.
Can AI models build a T-shirt store407? This was a cool read; also check out all the supporting docs she includes in the post.
Reception245 by ElevenLabs - an AI receptionist for small businesses.
How OpenAI plans to report models misbehaving41.
Slack Code83 lets your team and coding agents plan, build and review together
Pion172 - agents for running fully autonomous companies.
Which models are best at searching the web?223
Buzz130 - Your coding agent can ping your iPhone when it needs you.
Arrow 2 by Quiver107 - New SVG generation model. Their last one was way ahead of LLMs; curious how it compares with Astra now.
Code contracts124 - write down what your code must do, then have agents check it.
Self-updating docs111 from Mintlify. Now with ready-made automations.
An API to invent a dataset91 to train your models. (docs18)
TanStack Markdown86 - a tiny parser for docs, blogs and streaming AI responses.
Building a company brain439 people actually want to use.
A benchmark to answer how often AI agents cheat66.
Xiaomi’s AI team is streaming the RL run56 for their upcoming model.
What stays expensive when AI gets cheap210?
I made a website with 25 mini rooms, each with Claude keeping people company. Created with Claude Opus 5.
@kevin_t_ngo148
A quick EU founder survey: eusurvey.vercel.app.
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.…
@shuding33
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 me15 and Ben’s Bites
📷 thumbnail via @keshavatearth12
* sponsors who make this newsletter possible :)
Wanna partner with us for the next quarter?
Email us at shanice@bensbites.com9 or k@bensbites.com
New home for Cowork
the successor of LLMs
2,108 readers clicked at least once. 49 links, 49 with clicks. Heat is relative to the most clicked link in this issue.
Substack · essay