loehnsberg

With OLED, this is going to be the best e-book reader in dark mode, and given that it's water resistant you could even use it in bath/hot tub w/o destroying the device - if you're willing to put down $700 for an e-reader that is.

Are you sure this phone-only segment will pay twice the price for a little more screen estate? Maybe… But why not recommend to these folks to get an ipad mini with an e-sim? You get the bigger screen at less than half the price, and it still fits into the pocket of a coat at least. You could even buy one of those Logitech BT keyboards and have a mini laptop.

Kagi MCP works really well imo also within DeepSeek Harness. Just looking at cost neglects the possible difference in quality. How good is that DeepSeek web search/fetch?

It's interesting that in its marketing Meta compares Wonder to the closed frontier models but not the open (Chinese) models. By its own assessment, Meta could easily show how far ahead its own model is against the rest of the pack of open models but they chose not to. Why?

That is a lot of food. Even if I’d eat just that, I’d have to very consciously force myself to eat one kilo of that, unless it’s something like watermelon.

I run my own benchmarks at the interface of math and coding (ML, math-opt, stochastic models), and keep my own set of benchmarks, i.e. somewhat niche linear algebra and numerical recipes. DS-4.1 is the first open model that passes most of these benchmarks, and GPT-5.6-Sol is definitely not ahead. Even if it's all distillation, then DS does a formidable job at it.

Which quantization are you using there?

I have $10 and it resets every month; family plan.

Fully agree. The API via search and extract MCP works really well.

I noticed that my API quota resets every month. Have not been charged once.

This leaves a lot of questions. Why are they raising the age limit? What legislation demands this? Will other services follow? And what if parents give consent? Are users on a family plan now forced to kick off their kids from the joined plan?

Looks like StarCraft meets Starship Troopers but without that extra pinch of irony which likens this trailer to a fascists wet dream.

Maybe true for frontier LLM, but there's plenty of space in the niches. For example, I think their TTS/STT models are pretty good, speaking from personal experience.

This mirrors my experience:

- Store session turns in an sqlite-vec

- Provide the agent with an mcp to search the vec-db

- Let the agent write notes in md files along with an index / frontmatter

Along with the commit history, the vec-db gives the agent long-term memory. The notes allow the user to correct accumulation of false lessons.

Simpler but better.

There‘s only one truth, the rest is interpretation. I was looking for the non-Chinese interpretation.

Deepseek and GLM answered correctly on Openrouter when using non-Chinese endpoints. I hope it stays that way!