tosh's comments

On: When a video codec wins an Emmy

[tosh]

Technology and Engineering Emmy Awards

https://en.wikipedia.org/wiki/Technology_and_Engineering_Emm...

On: The Joy of Playing Grandia, on Sega Saturn

[tosh]

It would be great to have the saturn version + translation as well as the improved movie sequences

maybe there is a way to port them using the saturns mpeg add-on (?)

otoh probably fine to watch them on youtube in parallel

On: Rock Paper Scissors Solitaire

[tosh]

in german it’s

“Schere Stein Papier”

On: Dyalog APL 20

[tosh]

highlights: https://www.dyalog.com/dyalog/dyalog-versions/200.htm

On: What you can get for the price of a Netflix subscription

[tosh]

or an iPad instead of a yearly subscription

On: Apple's iPhone overhaul will reduce its reliance on annual fall spectacle

[tosh]

the iPhone is just the current name for the iPod

Steve Jobs:

  - iPod
  - Phone
  - internet communicator

On: Building more with GPT-5.1-Codex-Max

[tosh]

Codex CLI 0.59 got released (but has no changelog text)

https://github.com/openai/codex/releases/tag/rust-v0.59.0

On: Gemini 3 Pro Model Card [pdf]

[tosh]

This might also hint at SWE struggling to capture what “being good at coding” means.

Evals are hard.

[raducu → tosh]

> This might also hint at SWE struggling to capture what “being good at coding” means.

My take would be that coding itself is hard, but I'm a software engineer myself so I'm biased.

[Squarex → tosh]

It is just Python and Django. It might indicate qualities in other technologies, but it is not very good benchmark.

On: Show HN: Deta Surf – An open source and local-first AI notebook

[tosh]

Kudos on the launch. Love the local-ai approach.

Regarding open models: what is the go-to way for me to make Surf run with qwen3-vl? Ollama?

As far as I understand any endpoint that supports the completions API will work?

https://github.com/deta/surf/blob/main/docs/AI_MODELS.md

If I attach image context will it be provided to qwen3-vl? Or does this only work with the "main" models like OpenAI, Anthropic, Gemini and so on?

[aavshr → tosh]

Thank you.

Yes, we support any endpoint that supports the completions API. And yes, Ollama might be the easiest to setup. The images should also work with qwen3-vl.

But if you run into any issues, please feel free to submit a bug report https://github.com/deta/surf/issues

Edit: fixed github issues link

On: AWS multiple services outage in us-east-1

[tosh]

SES and signal seem to work again