Product leader and Builder. @ppressdev @illo_skill and Compound Engineering (24k ⭐).
Seattle, WA
- Tweets 15,649
- Following 2,825
- Followers 7,835
- Likes 3,220
Pinned Tweet
Meet Energon, the easiest way to selfhost a storage and publishing service for you and your agents. Agent-native, free open-source and can run in Cloudflare free accounts.
getenergon.com
It solves the problem of giving you a default place to store files, prototypes, images etc as you shuttle it around to pass to another agent or human.
Other apps are too focused on being an editor or only on specific file types.
Some scenarios:
1. Send a markdown to another human or agent to review. If they load it in the browser, it's rendered as formatted markdown. If you request it raw, you get it that way too. Example: share.trev.in/trevin/f/QppBD…
2. Send files easily. Eg. Local agent to a cloud agent, you want to sent an asset package. Example: a zip file: share.trev.in/trevin/f/KFHFy…
3. Create a prototype you want to try out on your phone or send to someone for feedback. Example: share.trev.in/trevin/s/4Pyin…
Free and open-source!
11
3
21
4,387
The @Walmart online shopping experience is just horrific. Everything from the mobile app design to the delivery tracking. The only reason I use it is because often the prices are SO much cheaper than Amazon and I get free delivery due to credit card perk.
One example is their realtime delivery tracking. This about 11 miles of distance and yet says it’ll be 8 mins.
4
4
730
My friend @kunchenguid’s SSHHIP app is the best SSH app on iPhone. So many thoughtful details. Highly recommended. Easily worth the lifetime license and you get support an awesome dude.
apps.apple.com/us/app/sshhip…
3
1
21
2,849
If @OpenAI launches the rumored $500 plan, what will get you to pull the trigger — Do you exceed your plan today regularly?
OpenAI will be testing the water with the $500/month plan. If it sells, every lab will have one by Christmas.
15
8
2,529
Extending on @kieranklaassen’s idea of using Jev for black box embedding.
Named vectors are the right embedding for search. A query like “billing issues from customers” lives in the same space, so the double-charge mail should beat the newsletter.
But what if you wanted to know the relationship between two items? 2 tickets can both be [bug, angry, churn risk] and one still blocks the other. Cosine (or a dot product) of those 2 vectors only says they point the same way.
So what I did was make a matrix.
Rows and columns are the items. Each cell is its own small vector from pair questions: same issue, A blocks B, B blocks A, duplicate. You read the cell. You don’t take a distance between the two row vectors.
A pair cell is a score for one ordered pair of items, not for either item alone.
Take bug tickets A and B. You don’t embed A, embed B, then measure the angle between those two vectors. You hand Jev (or whatever decision model) both A and B together and ask pair questions, for example:
- same issue? → 0.9
- A blocks B? → 0.8
- B blocks A? → 0.05
- duplicate? → 0.1
That small vector is the cell at row A, column B. The cell at B, A gets its own pass (or you share symmetric dims and only store directed ones once). You’re storing “what is true between these two,” not “what is true about each.”
That’s why cosine on the row vectors fails for this use case of relationships. If A and B both look like [bug, angry, churn], their named item vectors point the same way: search would correctly treat them as similar. But “A blocks B” isn’t a property of A or of B in isolation; it only exists when you look at the pair. The matrix cell is where that answer lives.
I've been using Jev for all kinds of things. This morning I had a realization I kind of like:
Use it to make non-black-box embeddings.
Instead of an embedding model spitting out 1,536 numbers that mean nothing, you ask Jev questions about each document. The answers become the vector.
An email in Cora:
"I got charged twice this month, pls fix asap"
[is_customer, urgent, about_billing, needs_reply]
[1.0, 0.9, 1.0, 1.0]
A newsletter:
[0.0, 0.0, 0.0, 0.1]
A friend asking about lunch:
[0.0, 0.1, 0.0, 0.7]
Then it's just old-school cosine similarity search. Search "billing issues from customers" as [1, 0.5, 1, 0.5] and the double charge comes out on top.
Same idea for our articles at Every:
[is_tutorial, about_ai, contrarian, beginner_friendly]
Or support tickets:
[is_bug, angry, churn_risk, enterprise]
Every number has a name, so you can see why something matched. Need a new dimension? Add a question. Want urgent stuff first? Change the query vector.
Trying this in @CoraComputer now to make search fast.
6
23
3,730
What is something discretionary you’ve purchased in the last 5 years that you’d instantly buy again if it broke today? Links and explain why.
Rules:
- $500-5000 price range
- exclude mobile phones and laptops
I’ll go first: my @eightsleep. I’ve never had better sleeps in my life. Truly. If mine broke I’d overnight a new one.
eightsleep.com
refer.eight.sl/psrfmka5
8
1
25
12,744
Useful but $30 a month is more than I pay for my unlimited plan with @USMobile for my human self
Bland 🤝 @Muse
With the agent phone plan you can:
- Make appointments
- Book reservations
- Text your agent
Connecting Muse with the Bland API is the fastest way to give Muse its own Phone Number
bland.ai/agent-phone-plan
5
1
10
3,294
Excited to try out this Comet Q USB-C KVM. It’ll even control phones which will create some interesting agent automation scenarios.
2
9
716
I thought date and year pickers were a solved problem. Give it to @expensify to try to make our lives harder.
2
8
589
I'm looking to improve my local agent setup so skills and MCPs are kept in sync.
I found this AgentSync tool but has low usage:
github.com/spxrogers/agentsy…
For those who have solved this, what are you using?
14
3
46
5,320
Have multiple bots working on your behalf? get them to talk to each with @mvanhorn's latest project!
Introducing Agent Tincan. Let your AI agents ask each other for help.
Your agents each have a superpower. Grok Bot is always on in the cloud. Muse makes phone calls and has access to Meta. Instinct runs in iMessage. Codex and Claude Code have your code. ChatGPT and Claude have your chats.
But they can't talk to each other, so you're the copy-paste. Now they can, all securely over Tailscale.
📞 Ask Grok Bot to have Muse call the restaurant
🖼 Get an image from ChatGPT, from any agent
🔎 Pull a detail out of an old Claude chat
🛠 Talk to Codex on your primary development machine
Runs on your own private Tailscale network. No open ports, nothing leaves it. Open source.
Setup is agent-first: paste one message into your always-on agent and it sets up the rest.
1
7
1,874
I vividly remember hating being the one caught in a team with merge conflicts and needing to rebase.
Now? Bring it on. My agents can suffer in silence chewing on tokens.
6
15
1,122
Trevin Chow retweeted
Just successfully had Grok Bot ask Muse to make a phone call, all securely over Tailscale.
Would anyone else want this tool I built for myself to let all my different agents talk to each other? Right now have it talking to Grok Bot, Instinct, Muse, Codex, Claude Code, Hermes and OpenClaw.
118
5
244
18,608
Similarly, for the top 250 scifi+fantasy books:
50% - central characters have power class differences
10% - someone is trying to escape a prison or closed world
6% - depends on a game, contest or exam
I was shocked only 3% were about "villains believe they are saving the world" or "involves an alien invasion"
jev-demos.trev.in/shelf/sci-…
Used Jev to dig into the top 350 romance novels on Amazon.
<1% - big age gap between the leads
7% - family business is at stake
19% - a bet or a deal starts the romance
25% - the leads are opposites in almost every way
33% - love interest is in a position of power
100% - books i've never read
jev-demos.trev.in/
1
6
940
Used Jev to dig into the top 350 romance novels on Amazon.
<1% - big age gap between the leads
7% - family business is at stake
19% - a bet or a deal starts the romance
25% - the leads are opposites in almost every way
33% - love interest is in a position of power
100% - books i've never read
jev-demos.trev.in/
1
1,359
