Hey folks,
I’ll be heading to SF on Thursday — speaking at Stanford the week after. I’ll be delivering live the ‘how to use agents if you’re not technical’ course I’ve been working on (ahem, still working on).
I’ll be in town chatting to LPs (my 2 prev funds; 2.3x MOIC, 43% IRR (2023), and 4x MOIC, 28% IRR (2020)) and founders (I invest in AI dev tools and infra!) - let me know who I should try and meet or any cool things going on.
The latest leak from Claude-land296 shows Anthropic is adding lovable-like features for building full-stack apps right inside Claude. Codex apparently had a similar leak (since deleted).
There’s a new term going around for products that agents can use - headless SaaS. Box’s CEO121 says that “Enterprises will kick out vendors that don’t make it easy/economical for agents to use their product”. And you can’t just wrap your APIs into MCP/CLIs208 and call it a day.
Talks at AI Engineer were across the spectrum from “code is a liability” to “slow the fuck down”. Alex has a good recap344.
Ben’s Bites is brought to you by Cloudera163
AI is booming, but ROI is lagging. The problem isn’t AI—it’s data readiness. Most enterprises aren’t as prepared as they think. See where things really stand in Cloudera’s Data Readiness Index163.
Claude Cowork153 is now generally available - out of research preview after 12 weeks with millions of users. Also, Claude for Word103 is in beta - draft, edit, and revise documents from the Word sidebar with edits showing up as tracked changes. (Team and Enterprise plans)
New Claude Code features - /ultraplan269 lets you build and edit a plan on the web, then run it in your terminal. The Monitor tool265 lets Claude watch for events in the background instead of constantly checking - saves a lot of tokens. Plus, an advisor strategy204 on the Claude dev platform that pairs Opus with Sonnet for better performance at similar/cheaper costs.
OpenAI added a new $100 plan49. Their own wording is too complex, so I’m stealing Theo’s57. Basically, $100 plan = 5x compute, $200 = 10x compute (where $20 plan = 1x). The bigger plans have 2x boost till May 31st, so effectively, $100 = 10x and $200 = 20x compute.
LlamaParse was built to tackle your most complex PDFs with the highest accuracy & the lowest cost. Now we want to put that to the test. Submit your ugliest PDF (dense contracts, financial tables, etc.), and judge the output vs your current OCR to win a Mac Mini. Can your doc outsmart LlamaParse?173*
Anyone can make a game now. Yoroll turns a rough idea into a branching, playable video-native game. Join waitlist to try.292*
Cursor cloud agents67 can now attach screenshots and demos to PRs they open. Your team reviews the artifacts directly in GitHub.
Shopify AI Toolkit158 - manage your Shopify store with your favourite agent. Works with Claude Code, Codex, Cursor, VS Code, and more. (docs34)
Open Agents217 by Vercel - open-source template for building coding agents.
How Missions work165 - from the Factory team.
Agentic parenting335 and TradClaw245.
The anatomy of an agent harness365 and a tutorial/walkthrough to build your own harness224.
Personal wiki tools inspired by Karpathy’s knowledge base idea - LLMwiki247, Wiki OS192, Hatch169, and GBrain169.
Evo202, another Karpathy-inspired CC plugin, optimises your code through experiments.
Ramp says their entire company is AI-pilled168. They even built a new internal product called Glass206 to give every employee an AI coworker.
getdesign.md401 - browse design systems of popular applications as markdown files. Preview instantly, install with one command.
Aqua Voice194 - premium voice keyboard for every app on your phone. Now on iOS.
Gitinspect104 - replace “hub” with “inspect” on any GitHub URL to chat with the repo. Runs in the browser, everything stays local.
Cloudflare Sandboxes107 are generally available - comes with a terminal, interpreter, live preview URLs & secure credentials. Sleeps when idle and wakes on demand.
The world is transitioning to a compute-powered economy. The field of software engineering is currently undergoing a renaissance, with AI having dramatically sped up software engineering even over just the past six months. AI is now on track to bring this same transformation to
@gdb197
PSA: You can vibe code your own "New tab" page in Chrome. I have turned mine into the ultimate solution to the "too many tabs" problem - See all your tabs with clear titles, grouped by domain - Closing any tab gives you "swoosh" sound and confetti effect 🎊 - "Easy wins" grouped
we just released the official Agent Skills for @supabase it's a set of instructions that teach agents how to build with Supabase correctly, including: ◆ Security and RLS ◆ Docs and product knowledge ◆ Schema management ◆ CLI + MCP instructions
Big personal news: I’ve been recruited by Google DeepMind for a new Philosopher position (actual title), focusing on machine consciousness, human-AI relationships, and AGI readiness, starting in May. I’ll continue my research & teaching at Cambridge part-time. Absolutely stoked!
Cursor's debug mode is great. But I wish i had it in Claude Code / Codex. Introducing debug agent skill: - /debug-agent [your bug] - writes logs and actually repros the bug - fixes the root cause
as more and more people start using pi, i now get this question often: "what are essential extensions i should install?" none. zero. start vanilla. only build/install something if you feel a recuring pain that you can't get rid of by reevaluating your workflow learned with
Read about me24 and Ben’s Bites
📷 thumbnail sourced from Twitter14
* sponsors who make this newsletter possible :)
Wanna partner with us for the next quarter?
Email us at shanice@bensbites.com16 or k@bensbites.com21
Big lab leaks
Headless software
2,963 readers clicked at least once. 47 links, 47 with clicks. Heat is relative to the most clicked link in this issue.
Substack · essay