I'm quite sure I'm in a bubble here, but not building with or for AI at this time in our lives would mean missing the biggest opportunity of our generation to create something amazing and make a big difference to humanity.
If I was retired, I'd come out with time and build. If I was already successful, I would still get my hands dirty and build. If I couldn't afford a computer, I would borrow one and build.
Is a "tool that Claude can use" the new SaaS?
If Descript completely axed their built in agent "Underlord", and instead exposed the tools and let Claude Code and Codex edit in their platform directly it would be the fastest growing editing platform in the world. Their transcript tech is world class, but they force you to use their built in agent. They will get cooked for this. Can someone please build the agent native descript. Please i will invest.
Want to know what your agents can see?
I'm building something that will tell you.
Sharing it here soon.
Yep, Andrej's suggestion works well.
A family member is needing tracheostomy (a tube into the throat to help with breathing) and I was researching how this impacts speech.
I got Claude Opus to turn my findings into an explainer video I can share with my family. Asked it to use my Elevenlabs account to generate the narration.
This took 10 min (including integrating Elevenlabs into Claude Desktop).
Can be improved but what a great way to share and explain.
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
Why are so many programmers/developers so unhealthy? They usually look like they'd run out of breath just climbing up a flight of stairs.
Experimenting with building a Claude mod that tells watches how you work and determines if you need a break :)
How's your mood?
I've noticed that my mood really affects a lot of the ways I think, make decisions, or analyse a situation.
If I'm in a good mood, my decisions are always based on hope, positivity and opportunity.
When I'm in a bad mood, my decisions are always based on fear or conflict avoidance, and an unwillingness to compromise.
This is one of the reasons I avoid reading the news and drastically minimise social media consumption. These channels are great at getting me down, especially if I start the day consuming them.
So now, whenever I need to make a decision on something or analyse situation: I check my mood. If I'm not feeling great or feeling negative, then I defer all that until I feel good again.
That will usually lead me to a better outcome.
farez 🇵🇸 retweeted
Or find a lifestyle where socialising is ingrained.
Really great effort in getting people together. But as you can see, it requires effort. And I think this is absolutely normal for people living in cities with a typical "city lifestyle".
There is an alternative where socialising feels less of an effort. Where the social part is in fact ingrained in the lifestyle.
I've experienced both. When I'm living in London, it takes effort and organisation to be social.
But when I'm in a small town or village, usually for surfing, climbing or snowboarding, I'm always surrounded by friends. Because those are usually activities you do with friends. And in between doing them, you're hanging out and talking about the activity you just did, or planning the next one. And the passion for these activities are like opposite poles of a magnet and bring people together so easily.
So yes, make the effort. Especially if you're in a city. But also consider a potentially healthier lifestyle that takes you outside of the city, outside of the tech/business bubble, and into nature and a more natural social setting.
If you’re learning how to use AI and AI harnesses to automate work, and want to go beyond the AI equivalent of “Hello world”, here’s a project idea.
Imagine you’re trying to reduce your work days from 5 to 2 days a week. And you’re going to hire a bunch of assistants to delegate work to.
Pick an open source AI harness, like Hermes or Hezo, and start building this assistant. Connect it to OpenRouter or LiteLLM so you can dynamically assign LLMs to different assistants. Don’t use OpenAI, Claude or Grok. They cost an arm and a leg.
Then pick one simple recurring task. Build your assistant for it. And delegate to it. Once this task has been fully AI automated, connect the next task. Then the next.
Apply this to real work. Not just made up tasks. The work must have consequence. Errors must have consequence. This will make you think hard about the design of these systems.
It’ll make you appreciate the effort that goes into building a robust AI workflow. And real knowledge that you can apply to your business or workplace.
I did this with my product, Pop Invoice. It’s a real world product with paying customers. I delegated all our development work to 2 Hermes AI agents that automatically pic up work tickets, plan them, do the development, and deploy a preview site for us to QA and feedback.
Using Hermes? Tip: use a smart Model for the main Hermes chat channel (the one that's making changes to Hermes's config).
I used a cheaper/weaker model thinking this is enough for general purpose chat, but ended up asking it to make crucial Hermes code changes, forgetting that it was running Haiku.
