YouTube Premium reforça a experiência com som de alta qualidade, IA na TV e mais novidades
🔗 https://tugatech.com.pt/t72036-youtube-premium-reforca-a-experiencia-com-som-de-alta-qualidade-ia-na-tv-e-mais-novidades

#AAC #android #base #blog #consolas #google #ia #ios #Opus #pip #shorts #velocidade #web #youtube 

I’m not sure if I agree with this statement from SoundCloud about Opus. It feels like they claim that Opus is outdated and inefficient, while it's actually the opposite.

Also Soundscloud started in 2007 and Opus was the right choice in the beginning? First release of Opus was in 2014 🤔
#soundcloud #opus

https://github.com/soundcloud/api/issues/441#issuecomment-3338113916

Microsoft abre o Copilot à rival da OpenAI e integra os modelos Claude da Anthropic
🔗 https://tugatech.com.pt/t71990-microsoft-abre-o-copilot-a-rival-da-openai-e-integra-os-modelos-claude-da-anthropic

#amazon #aws #azure #copilot #ia #llms #microsoft #OpenAI #Opus #tecnologia #web 

So sánh hiệu suất các mô hình AI lập trình Sonnet/Opus, GPT-5 và Code Supernova trên các tác vụ lập trình thực tế. Phân tích điểm mạnh, điểm yếu của từng công cụ khi giải quyết bài toán code thực tế.

#AI #Coding #AIcomparison #Sonnet #Opus #GPT #CodeSupernova #LậpTrình #AIVietnam #CôngNghệAI

https://blog.kilocode.ai/p/testing-code-supernova-vs-sonnetopus

TIL that FLAC is supported since Android 3.1, but Opus from Android 5 but not in an Ogg Opus file (.opus). Support of the .opus files was added in Android 7.

It surprised me, even though FLAC was released in 2001 and Opus from 2012. I thought that Opus is much older.

#flac #opus #android

Al fin me he animado a (volver a) guardar música en mi teléfono para casos en los que la cobertura falle.

Perdí las versiones lossy que creé a partir de los #FLAC que tengo en mi NAS, así que los he tenido que volver a convertir.

#Ogg #Opus, 128kbit/s VBR, full band, optimizado para música es muy eficiente, y si convertís desde una fuente sin pérdida (WAV, FLAC) o descargáis desde una plataforma que os dé varias opciones (como Bandcamp), lo recomiendo mil sobre MP3 salvo que vuestro dispositivo reproductor lleve más de 10 años sin actualizarse.
[Si puedes reproducir música desde Sp*t*fy, puedes reproducir audio en Opus]

Bloom county is back to save us all!

Apologies for the fb link, do please let me know if you can find this somewhere else...

https://www.facebook.com/berkeleybreathed/posts/pfbid02XnTJQ1wdge63MVygswb1Vw8ekgFjyScnujZk5djaFjt52GyNW132aRfJ6Hf6Bvk4l

#bloomCounty #opus #penguin

#Nyrdcast #Podcast 232: Coughs and Kids ft #music from #CallingAllCaptains & #beer from #4HandsBrewing/#2ndShiftBrewing

#podcasts #podcasting #podernfamily #movies #comicbooks #comics #DCU #RedHood #Batman #Deadpool #Superman #RobertRedford #Friendship #opus #odessa #freakytales @earshotmedia @podernfamily

https://www.nyrdcast.com/2025/09/nyrdcast-podcast-232-coughs-and-kids/

The switch from #claudecode to Open-Source tools and models works fine for me.

1. The CLI client I use is llxprt . This is a fork of the #gemini cli .

https://github.com/acoliver/llxprt-code

The Desktop client is #anythingllm

https://anythingllm.com/

Both have MCP support, and work for macOS and Linux.

2. For large code bases I am using ck search in my prompts and make llxpert to use it via Bash tool calls.

https://github.com/BeaconBay/ck

My experiences with claude-context are that it's expensive and not effective for the cost (embeddings):

https://github.com/zilliztech/claude-context

I stopped using it.

3. I mostly use #OpenRouter

gpt-oss 120b as a coding model

kimi-k2-0905 or glm-4.5 for select tasks, like finding a function or simple test output summaries.

These models are on par with #sonnet or #opus

https://artificialanalysis.ai/models/glm-4.5?model-filters=open-source

4. I mostly optimize my prompts, tools, and workflows.

I write my own MCP tools, and use specific RAG approaches to establish the context.

5. I self-host more and more. But I haven't found my stack here yet. I actually want gpt-oss, but it's too expensive.

6. #openai codex cli is a myth to me.

https://github.com/openai/codex

Yes, it's slow. But in numerous instances the output is great. It can be used with the same OpenRouter models.