swrrt

Does this kind of stream involves things like 'dynamic scaling' or 'load balancing' where typical streaming system need to consider about?

Interesting, I thought it was something related to Apache Kafka or Apache Flink type of things. I personally working on that type of streaming for a longtime, never considering stream in an 'agentic' context.

I just saw a video clip that introducing the naming of the US army equipment, with lots of wording like 'A M1 cannot pierce through a M1 but a M3 can'

Does someone want to make this into a product and selling to people?

Does a photo/image that generated/modified by a human-being using photoshop got protected by copyright? I think previously someone does this...

I know now we all are somehow like 'product manager' when using agent/chatbot, and we just need to setup requirements and point out issues. But in game area, I am not so sure models/agent are capable enough, especially involves heavy graphic related development and human interaction things? Since from my personal experience, even codex and claude code not so stable and efficient when dealing visualisation things like figures, videos and even much easier one - web-browser.

BTW, I also tried to make a entire LLM-driven bot to play boardgames like chess or mahjong, but it has the same latency issues since most of the online platforms have strict per-turn time limit like 15-30s, which is almost impossible for LLM/agent to react in time.

Seems visulization is still too expensive and sluggish. I tried to build things like tetris and snake eater with fable5 and got-5.6 sol, 90% of build successful in one shot and remaining needs 1~2 rounds debug. The whole experience is much better than months earlier, where a snake eater takes me 3~4 manually compile/run and input the error message and abnormal manually again and again.

But I am curious about building a larger scale game with/without professional engines like Godot. I highly doubt the model/agent is intelligent enough to setup the entire development environment correctly, thus may be struggle to test and debug themselves. Maybe something like GUI-agent a future?

How good is it to work on building games, compared to existing agents? I am building my own game?

Just asking, what is the recommended models for M3 MacBook with 18G memory? Seems modern local models are not available.

Taxi drivers in old days needs to remember the whole map of their city, I think that is an efficient exercising/training that recommended for anti-Alzheimer, just like playing puzzles or quiz for oldman? But nowadays it is all about google map, not so sure about the effectiveness.

Oh, it seems fine for me. I can login actually. Maybe network/server instability?

Don't think RAG is the most common method for now. In my knowledge now it is mostly about post training and reenforcement learning for adding specific knowledge to base model. RAG is mostly like an add-on to a fully trained model and not so stable or inherent?

Another trigger that automatically downgrade to opus4.8 again?

then you have a bunch of cables and wires that with all different types of connector that you can 'easily' identify which one is for which device. sounds familiar hah

Nice figuratively demonstrating, I think it can be a impressive lecture material if my teacher/prof use this kind of demonstration.

Sounds like a big-company issue, large scale lead to large burden and complexity.

Yep, offline mode is useful for edge devices also. I am considering deploying a extremely small model on steam deck actually.

Any visualised benchmark/scoreboard for comparison between latest models? DeepSeek v4 and GPT-5.5 seems to be ground breaking.

I heard someone said it is better than Opus 4.7. Recently, a lot of my friends complain about Opus 4.7 and previous models performance degradation.