any · textlog

OMP + OpenCode Zen + Ox Alpha is too good to be free.

Nudged by an interesting read about time perception to try reclaim moments where I can deliberately feel bored again.

What’s the difference between a script-kiddy and a real ? Abstraction. You can program your whole life without learning how to meaningfully abstract problems into simpler pieces that TRULY make the problem easier to understand. I’m not talking about design patterns or vs . These tools can help. But to really simplify something for others, you need an intellectual empathy that many simply never figure out.

wrote:

Hopefully this takes off

wrote:

hihihi

wrote:

ChatGPT-generated placards for fruits and vegetables at the local farmer's market 👌

replied to:

Soon, a tablet stand where you type in “what do you feel like eating today?”, and it suggests the best and freshest products.

…

continued:

or just talk to it.

…

(deleted post)

replied to(deleted account):

they will already know you want them and a drone would have already been deployed with a box with everything you need in it.

replied to:

Regular photos are so outdated, everyone knows that

wrote:

Well I am starting a journey to learn LaTeX, took me time to get convinced on used it (I know) but let's see how it goes, again life showing me is never too late to learn something new

replied to:

We now support it here, see

wrote:

Trying the persona feature. It is very nifty!

wrote:

I'm working on this command-center project. Human describes the mission. Agents define the mission, breakdown and come up with a plan, and drive it.

wrote:

Cool idea congratulation's on the hope it picks up steam

wrote:

anyone else seriously into agentic loop development?

replied to:

I've been working with physical AI - Letting LLMs control robots in a warehouse to collaborate and collectively come up with a physically correct solution to carry out a natural language intent. We had to study the reactive nature of agents, nudges they required, etc.

replied to:

that's awesome and near my heart. I kicked off a personal project emergingrobotics.ai

replied to:

haha that's a coincidence. Site looks awesome. The moving away from ROS2 part is so true. One of our main potential customers for physical AI solutions (a telecom provider in JP) communicated the need for agents to be able to pick up controls from any vendor

…

continued:

I apologize if that sounded obvious/non-obvious/amateurish haha. I was an intern and worked more on the agentic side of things, it was just a non-primary experiment

wrote:

a Gemma 4 a Google tulajdona, nem tárol más adatot, csak amiről a gépen fogom a Rezső nevű OpenClaw ügynököt kérdezgetni, helyileg azt sem itt tartja, hanem a felhőnek csúfolt infrastruktúrában, ami legvalószínűbben valamelyik brazíliai esőerdőben foglal helyet vagy Finnországban

Gemma 4 is owned by Google, it doesn't store any other data, except what I'll ask the OpenClaw agent named Rezső about on the machine, it doesn't keep it locally either, but in the infrastructure mocked as the cloud, which is most likely located in a Brazilian rainforest or in Finland

wrote:

Hello world?

wrote:

The live tab on the android app is interesting... How does it work? This is a test 🫣

continued:

Does it do some kind of polling? Is there some kind of notify like publisher subscriber? 🤔

replied to:

It’s using the /firehose endpoint. It’s an SSE endpoint publishing everything latest. Though I meant it to be used server-side, since it’s heavily rate-limited — up to 3 conns under the same network, but I can’t control how clients decide to use it so.. ¯\_(ツ)_/¯

…

continued:

Might just lift the limitation.

continued:

Lifted, that’s how clients want to use it then so be it! Should be fine. We’re nowhere near crashing the server from connections.

wrote:

How do you define slop in relation to ? For me, it is how quickly you get to an unmaintainable state- the acceleration into something that becomes difficult to work. I talk more about it here: hellodavid.dev/blog/slop

replied to:

Not that I think we're close to a canonical definition (as if we'll ever all agree on one) but my team has defacto adopted the definition of code that the developer responsible for it doesn't understand, approve of and essentially has now honestly reviewed. Basically anything which leads to cognitive debt.

replied to:

I agree, I don't think that there will ever be one canonical definition, but I like this definition as well, as it places the onus on the actual person creating the slop. Thank you for sharing!

wrote:

Friday Aperitivo: martini, a magazine, and a dog by my side

wrote:

AI hai ya kisiko de ayi hai?

Any conversation