nox

AI: the genie we can’t put back in the bottle

[nox @noxlonga]

soon there will come a day when i write my last line of code

[nox @noxlonga]

@OrganicGPT same experience. gemma4 31b dense bf16 > same qwen3.6 for my usage (hermes, chat, my apps). have you tried quantized ? i'm shocked - same perf for the way I use. https://t.co/V93S3aFrq8

[Google Gemma @googlegemma]

We just dropped Gemma 4 Quantization-Aware Training (QAT) checkpoints on Hugging Face!

All Gemma 4 model sizes and their drafters are now optimized with QAT to cut memory requirements and maximize on-device performance!

[nox @noxlonga]

@jenzhuscott I did personal app, only I use. Also clone of a game from google play without ads and other limits for my family, plus added multiplayer mode missing in the original one. not going to sell anything.

[nox @noxlonga]

@wakufactory Upvoteお願いします！ https://t.co/dU2tsLTpWW

[nox @noxlonga]

@ajambrosino @argofowl as there is still no codex app on linux, linux will miss chatgpt too. aha

[nox @noxlonga]

@ajambrosino today, use it in Notepad++/VScode search everyday. not complex ones though, like lookbehind

[nox @noxlonga]

@MrPeterLMorris /btw, check @digitalix yt videos how to replace 1tb ssd with 4tb, and moving to faster bus. you can save simply by replacing + if you sell 1tb - more

[fofr @fofrAI]

Slinky dog (Made with Omni)

[Mark Kretschmann @mark_k]

Clearly, Google Omni has been wildly underrated.

Here it's turning a normal human hand into a live anatomy demo! Letting you see the muscles, tendons, and cartilage as if the skin were removed.

Brilliant for educational purposes!

[nox @noxlonga]

@JustinBleuel @ChatGPTapp i see this on linux

[Seth Howes @SethSHowes]

I just sequenced a human genome to 30× coverage entirely at home.

As far as I know, this is the first time this has been done.

I didn’t step foot in a lab once. Every step - from saliva collection, to running the sequencer - took place in a single room with a dining table + kitchenette.

Six weeks ago, I had never done wet lab biology before.

I used an Oxford Nanopore P2 Solo - the only commercially available sequencing device portable enough to do 30x human genome sequencing at home.

Biggest takeaway - I could build something that combined software, hardware, and molecular biology far faster than I thought was possible.

I can name >100 specific instances where AI helped me solve a technical problem that would previously have blocked me because I lacked access to a domain expert.

For example: how do I save my sequencing run when my DNA extraction yield is 4x lower than I need it to be, and I have this limited set of reagents to hand?

To make this work, I had to navigate multiple disciplines:

- writing software to monitor sequencing runs and orchestrate remote GPU infra for basecalling
- learning + executing 5 hour long molecular biology protocols
- building a hardware device to quantify DNA concentration

Apologies for the hyperbole, but I feel super lucky to be living in 2026.

A few weeks ago I decided to sequence a human genome to 30x at home.

Then I actually did it. And I did it really quickly.

[nox @noxlonga]

@OfficialLoganK @jbscript

[nox @noxlonga]

@_mohansolo hi, is it OK that ag-IDE tells me about avail update but for new agi which is already installed? IDE shall inform about IDE's updates. no?

[nox @noxlonga]

@OfficialLoganK @antigravity why antigravity IDE tells me about avail update of antigravity?

[nox @noxlonga]

@Firebase "installing all necessary components" - where will they be installed - on host? can I have isolated docker container for this?

[nox @noxlonga]

@thsottiaux run on linux

[nox @noxlonga]

@GaryMarcus using it for simple tasks: reminders, price watch, news aggregator. trying to use only local models - so only small tasks.

[nox @noxlonga]

@ajambrosino but cannot live on linux. hm, mysterious linux, codex cannot port itself there

[Jun Song @jun_song]

로컬LLM 모델을 잘 활용하는 방법 중 하나 :

사용중인 Codex, Claude에게 스킬을 만들어달라고 합니다.

“앞으로 너는 오케스트레이터고, 로컬LLM은 너의 지시를 따르는 부하야, 로컬LLM은 너보다 멍청하니까 지시를 내릴땐 아주 구체적으로 줘야해, 그리고 앞으로 니가 할 일은 계획을 짜서, 지시를 만들고, 작업물을 평가하는거야.”

이제 당신은 $200 구독에서 $20 구독으로 변경해도 사용한도가 충분합니다.

[nox @noxlonga]

@bnjmn_marie I switched from qwen3.6 to gemma4 and it was relaxing. almost immediate answers for hermes requests. (comparing sparse models on dgx spark)

[Mark Gadala-Maria @markgadala]

Love this.

A day in the life of different planets in our solar system brought to life using AI.