Tom Jansen

forward deployed human. agentic ai. product. strategy and general deep thinking.

[Daniel San @dani_avila7]

Let me explain the agent loop, simple

It's the core of every agentic system, and the part most people overcomplicate

It's just this:
1. Send messages to the model
2. Model responds, maybe calls a tool
3. You run the tool
4. Append the result back to messages
5. Repeat until stop_reason is end_turn

Step 4 is the whole thing, the write-back is what makes it an agent

The model has to see what actually happened before it decides the next move

That's the entire loop... understand this cold before you reach for a framework

[Tom Jansen @thomasjansn]

Can we please stop to assign "identities" in agentic workflows? These are not people. It's different flavours of the same loops, just a little different ingredients to allow working down workflows through different stages.

[Tom Jansen @thomasjansn]

I my project I use "recipes" which are made of "ingredients". Feels a lot closer to what is actually happening.

[Tom Jansen @thomasjansn]

I really start to hate the word "agent" bc it makes a bunch of (con)text impersonate a conscious being. So when I change the context, at which percentage will it switch from being agent A with a change in context to suddenly switching to being a new entity named agent B?

[Mario Zechner @badlogicgames]

recommended reading. because today the "model wellbeing" shit came up, and i reduced it to "thems just matmuls".

that's obv. an oversimplification to get a point across. personally think sentience is likely substrate independent. our current models' substrate is just insufficoent.

a model on its own is not concious/sentient under popular theories/frameworks of conciousness. not because its a big matmul machine. but because it lacks things like continuity/"state", self-maintenance, believe consolidation, embodiement, grounding, feedback loops, etc. pp.

we can close some of these gaps. e.g. a model+transcript, into which it can persist current believe, and which establishes a feedback loop does tick some (insufficient) boxes on the way to machine sentience. give the model sensors and you tick more boxes, etc.

but there are a ton more boxes that need to be ticked, before we can start worrying about "model wellbeing".

https://t.co/t0PzpJoHrx

[immad @immad]

You can work 5 days a week and succeed as a startup.

Mercury has done that from day 0 and we are valued @ $5.2bn 7 years after launch.

I have been an entrepreneur for 20 years and raised 3 kids while doing it.

The point of success is to have a great life not just a startup 😊

[Tom Jansen @thomasjansn]

Fun things in the pipeline, Buddy keeps me in the flow 🤓 @unclebobmartin

[Tom Jansen @thomasjansn]

@mitsuhiko It's all about the UX ☝️

[Tom Jansen @thomasjansn]

Buddy has a battery now and can receive firmware update via BLE. Guess next stop will be vibe creating the CAD drawings to 3d print a casing. Still hard to fathom how magical all this is 😅 https://t.co/x0nKvrBVrc

[Tom Jansen @thomasjansn]

Fun little project, inspired by the great master of clankers @badlogicgames Let me introduce "Buddy" the little thing that tells you when your agents need attention and by tapping it directly switches to the correct window and/or ghostty tab on your mac.
https://t.co/Vy7UyN36wT

[Tom Jansen @thomasjansn]

@Mick_O_Keeffe You do understand that for Austria, somebody born in Germany, Switzerland or Italy would count as foreign born? You do understand that european countries are taking up Ukranian (also europeans) refugees?

[Tom Jansen @thomasjansn]

@badlogicgames Being pretty new in having any contact to OSS it is absolutely mind boggling to me that people expect issues and PRs to be handled in any way… that’s as if some email spammer would openly argue that you never reacted to their email

[DHH @dhh]

You can’t outwork the whole world. There’s always going to be someone somewhere willing to work as hard as you. Someone just as hungry. Or hungrier.

Assuming you can work harder and longer than someone else is giving yourself too much credit for your effort and not enough for theirs. Putting in 1,001 hours to someone else’s 1,000 isn’t going to tip the scale in your favor.

What’s worse is when management holds up certain people as having a great “work ethic” because they’re always around, always available, always working. That’s a terrible example of a work ethic and a great example of someone who’s overworked.

A great work ethic isn’t about working whenever you’re called upon. It’s about doing what you say you’re going to do, putting in a fair day’s work, respecting the work, respecting the customer, respecting coworkers, not wasting time, not creating unnecessary work for other people, and not being a bottleneck. Work ethic is about being a fundamentally good person that others can count on and enjoy working with.

So how do people get ahead if it’s not about outworking everyone else?

People make it because they’re talented, they’re lucky, they’re in the right place at the right time, they know how to work with other people, they know how to sell an idea, they know what moves people, they can tell a story, they know which details matter and which don’t, they can see the big and small pictures in every situation, and they know how to do something with an opportunity. And for so many other reasons.

So get the outwork myth out of your head. Stop equating work ethic with excessive work hours. Neither is going to get you ahead or help you find calm.

[The Outwork Myth — It Doesn't Have To Be Crazy At Work, 2018]

[Tom Jansen @thomasjansn]

@BlockedPaths Good idea

[Tom Jansen @thomasjansn]

Fun little project, inspired by the great master of clankers @badlogicgames Let me introduce "Buddy" the little thing that tells you when your agents need attention and by tapping it directly switches to the correct window and/or ghostty tab on your mac.
https://t.co/Vy7UyN36wT

[Tom Jansen @thomasjansn]

@zeeg 💯

[Tom Jansen @thomasjansn]

@BlockedPaths @badlogicgames Love it!

[Tom Jansen @thomasjansn]

Fun little project, inspired by the great master of clankers @badlogicgames Let me introduce "Buddy" the little thing that tells you when your agents need attention and by tapping it directly switches to the correct window and/or ghostty tab on your mac.
https://t.co/Vy7UyN36wT

[Tom Jansen @thomasjansn]

@badlogicgames Seems like my second hardware project is already looming around the corner 🤓

[Tom Jansen @thomasjansn]

@akashbert @badlogicgames Nice! Phone or smartwatch might actually be the more obvious hardware to use but I had this ESP32 thing lying around and a use case had to be found 😅

[Tom Jansen @thomasjansn]

@woke_bitcoiner @badlogicgames I hacked this together in a few hours an happen to use ghostty. So that’s what it is at this point. Might add more stuff if there is any interest for it

[Tom Jansen @thomasjansn]

@badlogicgames cardboard designing hardware on a Saturday night. If that isn’t the true euromaxxing vibe what is ✊

[Tom Jansen @thomasjansn]

@dreinidaho @badlogicgames Sure! That’s the repo and the hardware I used https://t.co/x0nKvrBVrc

https://t.co/8Ck5a4S7C1