Alifatisk

Why censor yourself?

Maybe I should go back to ChatGPT again and copy-paste code.

Bummer, this does not affect the weekly usage on Codex through Subscription.

”The effects of consuming negative news during the workday can linger in employees' minds long after they stop scrolling.”

Doomscroll doesn’t necessarily have to be about negative news. I don’t have any social medias but I’ve seen my friends feed, they are pure brainrot.

Does it exist in the web at all? Could be the contents have not been scraped for the dataset yet.

Can one try out this photoscanner?

Duopoly

Right, I guess the ”Open” in OpenAI means open for speculation.

Is Luna MoE? Had no idea OpenAi went that direction

How about "lactose bigotry" instead of "lactose intolerance" https://scholar.google.com/scholar?q=%22lactose+bigotry%22

Thank you Kenny

> I'd gladly take A5B or A8B or even A10B as a sort of middle ground.

Whats up with focusing on the active param count? Do yall fiddle with the weights or something?

Didn’t know I was basically replicating AGENT.md. I didn’t jump on that train when it became a trend.

We’ll see, the best benchmark is your own. Looking forward to try this out!

I am not sure this enlightens you with anything but I have a TODO.md file with three headlines. Todo, Doing and Done. The agent is aware of it and knows on which task we are on.

On complete, it moves the user story from Doing to Done. I also have a MEMORY.md file that the agent read and writes in the beginning of a new conversation and at the end of our conversation to update stale information. These files are referred to every time I start a new conversation.

Regarding forking, I know Codex has such button underneath each message that lets you fork the whole conversation. I usually do that when I want to sidetrack and discuss something.

I use no SKILLS or commands like /goal. I’ve come a long way with just prompts and markdown files. Its all a different way of encapsulating instructions anyways.

Does it reset at every turn? From my experience in Codex for example, Luna (Max) fills the 256k token window relatively quick. The only thing lowering the context window again is the compaction.

What I do currently is having a markdown file named MEMORY.md at the root folder. Then, whenever I create a new conversation with an agent, I refer to that file. That file becomes the initial source of context and knowledge. At the end of an task, before I leave the conversation, I ask the agent to update MEMORY.md with lessons and new knowledge it has gathered from our conversation, it also removes stale or outdated information from that markdown file.

I myself do not care what's written in that file, I steer, instruct and share my knowledge, visions, goal and preferences in our conversations, and the agent will boil that down and update the markdown folder. It has worked very well for me.

I now do not have to worry about creating handoff prompts when creating a new conversation or that I have to teach an agent from the ground up about the context we're in, I just refer to that markdown file.

Ever since the insane discount with GPT-5.6 Luna, not much excites me anymore. I mean just look at the benchmarks, even though Gemini 3.7 Flash performs well on the DeepSWE 1.1, Luna (Max) still performs way better. I personally have stuck to Luna (Xhigh) because its been more than enough and does not bloat up the context window too fast with reasoning tokens.

https://deepswe.datacurve.ai

> Starting January 1, 2027, $1.50/1M input tokens and $7.50/1M output tokens will apply.

Compare this to Luna which is at $0.2/1M input ($0.02 cached) and $1.2/1M output.

https://developers.openai.com/api/docs/models/gpt-5.6-luna

I mean at this point, no news about what the current US administration is doing is shocking me anymore. I am exhausted. It is what it is at this point, Trump will continue as usual, richer people get richer, republicans will excuse this behaviour and point fingers somewhere else while the rest will continue to suffer. I feel like we are in some sort of endless loop.

Trump does something > We react with "ooh no, orange man bad" > Dust settles > Get amnesia and continue our lives > And the cycle repeats

So its a competitor to Homepod and Alexa, but more capable, possibly through Computer Use among other agentic workflows people have today.

I’ve read this sentence for more than a decade now.

What? Does using sbx require login? Bummer.

Looks interesting, might try it out. I have to ask, did you really need to hijack my scroll behaviour?

Seems like that's the only way at the moment. Create a good general handoff prompt and turn it into a SKILL.

No, but after looking it up, his skill doesn't differ that much from how I do it, with prompting the agent to boil down the whole conversation into a handoff prompt for context to next agent.

You mean like a SKILL?

With clean I mean the opposite of how I currently do it, which is by asking the model to compact the whole thread into a prompt which will act as context for next model.

My way of prompting this varies and every time I receive the blob of output, I can’t fell how well it managed to capture the necessary details. This way feels lika a dirty way to transfer knowledge from one conversation to another.

You said there is? What’s the options?

I wish there was a clean way to compact the conversation into a prompt with all necessary context for a new fresh conversation.

Thank you!

Doesn’t show anything except searches for MU?