370 Photos and videos
Jun 11
Agentic coding is a ladder, and I think it's most effective to climb it one rung at a time.
Loops are very powerful but if you try to jump straight there without first understanding both interactive and unsupervised agentic tasks you're not going to build effective loops.
2
1
3
233
Jun 11
My personal experience has been that I get comfortable with one rung and then eventually start feeling "cramped" as I master the current toolset.
Then (and only then) I start trying the next level of abstraction to see if it works for me.
133
Jun 3
One pattern I find myself reaching for frequently these days is to gather data into a heavy JSON "kitchen sink included" format and then build lightweight CLI renderers that slice and dice the data into various token-efficient text views for an agent to understand.
121
May 23
This is a blessing and a curse. I sometimes find myself starting from scratch over and over, never committing to "good enough" bc I know how easy it is to do the next version.
Sunk cost is a fallacy but I think sometimes it's also a useful heuristic to force you into finishing.
May 22
what I love about working with coding agents is that starting over is essentially free.
after implementation, I can objectively review and if I'm unsatisfied, I can just revert everything and start afresh... with new lessons learned.
if I implemented the solution by hand and invested hours into going down the wrong path, it would be harder to convince myself to just throw it away, ya know
1
2
7
2,681
May 16
My new bar for onboarding is "give me a prompt I can paste into a halfway decent agent that gets me completely set up and onboarded to your service with no prior knowledge of how anything works".
Results are graded on a scale of how much work I have to do instead of my agent.
1
1
205
May 16
This actually works as a bidirectional grading system for evaluating agents as well. If Agent X can get it done smoothly from the prompt but Agent Y can't, the service or the agent or both have work to do.
109
May 15
3 things every LLM API ought to have knowing what we know now about building agents:
1. Allow add'l function defs without busting prefix cache
2. Interleaved "developer" messages with stronger instruct weight
3. Canonize XML-tag-ish structure into first-class "section" primitive
1
2
114
May 12
Every social media service needs:
1. A "slop" button that is a combination user mute and report of a post as being low-quality.
2. ToS allowing discretionary banning of users for automated low-quality posts.
Right now slop replies are clearly rewarded. They need to be punished.
1
1
120
May 12
Waiting for a reply shaped like this on this post:
"A slop button changes the game on automated posters. One click and the post is gone. It's not just cleaning up the timeline, it's changing the incentive structure."
🙃
1
82
Apr 20
I wanted to play around with building a personal agent for my family and the process of getting working credentials to talk to a chat app is...next to impossible?
Is there some secret shortcut to doing this that doesn't require me to register an LLC or something?
3
1
471
Apr 20
Okay so it turns out Telegram is 1000x easier to set up with a bot than WhatsApp or Google Chat or SMS.
I don't use Telegram generally, I didn't particularly want to start, but I might for this reason alone.
1
154
Apr 19
This was something I really wanted in Go, but now it's hard to be excited because I basically don't write code by hand anymore.
A rare moment of post-AI melancholy for me.
The following #Golang code doesn't compile now. But it is very possible to compile since Go 1.27.
github.com/golang/go/issues/…
package main
func fieldValues(s struct{x, y, z int}) []int {
return {s.x, s.xy. s.x}
}
func main() {
_ = fieldValues( {(x: 1, y: 2, z: 3} )
}
3
3
590
Apr 13
I think the most common frustrating architecture decision I run into is:
- To do X (thing we want to do a lot, like define a new tool for an agent)
- You need to add code to Y, Z, A, and B
Features that need to scale should have vertical consolidation of their definitions.
1
201
Apr 12
Which of the chat platforms are adding streaming message support for better UX for agents in chat?
1
1
266
Apr 6
An interesting thing about the AI era is you no don't need humans to figure out "how" or "what". New to a codebase and need to trace a code path or discover relation between components? Ask an agent.
Now most questions to my teammates are about rationale or judgment - the "why".
1
2
283
Mar 31
Putting Tweetdeck behind the $40/mo paywall with no legacy pricing and no notice is...a choice. It was worth paying a few bucks a month for, but no thanks I'm not shelling out 10x as much.
1
415
Mar 19
Google Wave is a pretty perfect conceptual interface for AI multiplayer human collaboration.
1
5
213
Mar 11
How can my sense of nostalgia be so strong for something that only happened 2.5 years ago?
Mar 10
pov: it's 2023, you just discovered AI, and you're building your first GPT wrapper project
7
303
Michael Bleigh retweeted
Mar 10
Announcing Genkit Dart (Preview) ✨
Build high-quality AI apps that run anywhere 📱💻
In this release:
✅ Support for Gemini, Claude, OpenAI
✅ Type-safe AI flows
✅ Dev UI for AI testing and traces
✅ Run code on client or server
Read the blog → blog.dart.dev/announcing-gen…
2
52
221
60,708
Mar 8
The Doom novelizations from the 90s included a plotline where the space marine was forced to relive his experience fighting alien demons on Mars over and over in a simulation.
Let me explain what just happened, because I don’t think people realize how INSANE this is.
> Cortical Labs put 200,000 real human brain cells onto a silicon chip and trained them to play Doom in just one week.
> Each CL1 system costs $35,000.
> A rack of 30 units consumes only 850–1,000 watts combined.
> The human brain operates on 20 watts.
> Large AI training clusters burn through megawatts.
>Backed by In-Q-Tel.
115 units began shipping in 2025.
> Cortical Labs is selling “Wetware as a Service” through Cortical Cloud, letting developers deploy code remotely to living human neurons with no lab required,
> priced like a software subscription but powered by real brain cells grown from adult skin and blood samples.
> it isn’t about gaming, it’s about biological computing that could eventually outperform traditional silicon in energy efficiency and adaptability.
This is getting really scary and we’re still at the very beginning.
1
347