Ok bad stories about VCs are spreading on X right now, but VCs have horror stories about founders too
Like, that one time when a founder decided to take another term sheet with a higher valuation despite our obvious ability to add value, thought leadership and vendor discounts
Coding is basically the pinnacle of what you could reasonably automate with AI, and yet we still need human engineers to oversee agents for them to be effective.
The AI models are trained on an incredible amount of sophisticated code. The users are highly technical and can use the latest tools quickly. The work is “verifiable” because you can test an app. The outcomes are often removed from the quality of the code (you can have sloppy code but the app can still work). And the context for the agent is often already digitized and sitting in the codebase.
That’s an incredible amount of benefits that AI coding agents get to work with. Some of those apply to knowledge work, but most don’t in areas where the work needs to be fully reviewed to be useful, or where data isn’t as abundantly digitized. This makes the job for agents in knowledge work more complicated.
So if with all of that, engineers still remain in very high demand, the risks are going to be less than what’s perceived for other areas of knowledge work. Agents will let people do far more than they did before, but the people don’t go away.
designing in code is now as easy as:
click, chat, hold shift to multi-select.
works best with Composer 2.5 https://t.co/jKDWktp69K
Agent filesystem state can now be read, written and mounted independently of Sandbox lifecycle.
We’ve been developing a novel virtual storage infrastructure solution for all our compute products.
Storage that’s decoupled, but attachable to Builds, Functions, Sandboxes & more. https://t.co/x2CJpPHf62
Shoutout to @andrewqu founder and CEO of https://t.co/pYz1Gn97jD 😁 you can just ship things https://t.co/YfqUgl5zCm
Use the Skills API to make all your agents and platforms smarter.
Think of it as the npm registry for agent capabilities and extensibility. Free and open. https://t.co/kcVnJSupTf
Cowork is at its best on work that’s too big for a chat: research across dozens of accounts, recurring reports, triaging my inbox and drafting replies.
If you’ve been curious, this is a good month to find out what it can take off your plate. Can’t wait to see what you do.
We doubled Claude Cowork usage limits for the next month. This applies to your 5-hr rate limits. If you’ve been saving up a big messy project, now’s the time. https://t.co/qwjn8cVTUk
a smarter alternative to "always use plan mode":
always frame your task as a question, so that the model is invited to push back and rate the quality of the idea/suggest alternatives, rather than blindly execute what you SAID to do
(which is often not precisely what you MEANT)
literally just appending "?" to the end of your prompt often does it
i love being (for now) bdfl for aie because i can do cheeky shit like the AGI pills we did in london and also this https://t.co/dXoPfxlKd0 https://t.co/DS4J7hY1gF
@aiDotEngineer lmao designer vincent back at it again with the frontier capability tests https://t.co/I6OoTDbs5E
Just interviewed @mvanhorn and I'm so inspired.
I had no idea that he has no CS degree or real engineering background.
Despite that, he has shipped so many awesome projects and contributed to repos like Python and Go.
He does swear by @every's Compound Engineering for making good plans and shipping good code: https://t.co/L8JrNQfyPb
📌 Will clean up the interview and share soon on my YouTube: https://t.co/1C6pbWzPYn
How to build AI skills that check their own work and improve over time:
1. Give it context
Ask AI: "Create a skill for this [repeated task]. Here are examples of good output so it knows what good looks like."
2. Make it easy to trigger
“Write a clear skill description using this pattern: Use when the user wants to [do this].”
3. Add evals
"Create an evals md with 10 pass/fail checks for common errors in the skill's output."
4. Add memory
"Create a memory md to capture one-sentence learnings from past chats using this skill."
5. Build a skill to edit skills
"Create a skill that cleans up other skills by removing duplicate or stale instructions, vague rules, and AI slop."
📌 Watch my full walkthrough here: https://t.co/u434ytNSZd
GBrain gives OpenClaw and Hermes Agent wings https://t.co/gUt6ll33Vn
You can now finally try one of those big projects I was teasing that I started working on a few months ago.
We want this to over time get better at helping you learn the best techniques to build better software, faster. https://t.co/hQpYCpl9JB
This is the definition of must-have for the future drone war. https://t.co/m33IZgh1Dx
One of the most common mistakes I see enterprise AI teams make is building for today’s model capabilities and price points.
Think 6 months out. Models will be way smarter and cheaper.
Scaffold around today’s model weaknesses to push the frontier. Bet that the next generation of models will natively solve for the scaffold. Push the frontier again.
Build for the slope.
Over time, that ability to repeatedly identify and bridge model gaps becomes a moat of its own.