JaddedFauceet

@JaddedFauceet@lemmy.world

This is a remote user, information on this page may be incomplete. View at Source ↗

⁨Comment⁩ on ⁨AI controls is coming to Firefox⁩ ⁨⁨1⁩ ⁨week⁩ ago⁩:
How about giving it a try.

If you happen to have work that is primarily text based (like programming).

Pick something that you have expertise on, and see LLM can help to automate it. Usually this require using LLM with tooling that provide agentic capacility (if you are into this, checkout opencode / Kilocode / Roo code).

Once you get a hang on it, try to mix it up with skill gap that you are less knowledgeble of, but have an idea of what you are trying to accomplish. This is what fascinate me.

Don’t jump straight into vibe coding or domain with 0 knowledge and expect good and repeatable result (not now at least).

In my case, I am a Web UI developer, I have quite an extensive knowledge on that. For serious work, I can provide (or get it to reference) my requirement, so that it create close to 85-95% of what I need. I can easily verify and make modification. If not, just delete the entire work, refine my original idea and ask LLM to try again.

But occassionally I need to test my work on Native iOS and Android device. These are not my expertise and I have no interest in learning them yet. In the past, I will either get help from someone to build a prototype for me, or learn and read docs to create a lower quality outcome.

Now, i ask LLM to create a prototype in 5 minutes. Then add different scenario and features in the next 5 minutes, allowing me to test my work and iterate much faster. If I really want to do that myself, it may take a day or 2, time that I could have spent improving my own work.

These are throw away work that will only be used a few times. I don’t care about maintaining or debugging it.

Another case is again report and visualization generation for data. Instead of reading several pages of documentation on how to create these visualization and trying to architect the data flow. Now i just ask LLM to “given this data that shows the relationship between x and y, create a report with visualizatiom focus on xyz”.

Nowasday LLM produce work that already surpass what a junior-mid developer can produce. And if I am not satisfied with the work, I will just delete the entire work and redo. No hard feeling, no need to convince the orher person that their time has just gone to waste.

The only worry I have now is when people stopped learning because of this. And that companies stopped hiring new junior developers.

Without junior developers, there will be no senior developers. Or maybe LLM will eventually make expert obsolete? Right now I don’t think it is possible yet.
⁨Comment⁩ on ⁨AI controls is coming to Firefox⁩ ⁨⁨1⁩ ⁨week⁩ ago⁩:
I can get LLM to write prototypes and demos in the background while I am working on other parts of the code at the same time.

with the right prompt, I can generate and scaffold documentation pages, which I may not have time to do so.

Things are happening in the background and I get more done.

I feel like I am faster?
⁨Comment⁩ on ⁨AI controls is coming to Firefox⁩ ⁨⁨1⁩ ⁨week⁩ ago⁩:
LLM is a subset of ML. Now screen reader also use LLM to describe image for visual impair users.

Some of these are tiny LLM that run on mobile hardware.

There are also LLM that specialize in translation (TranslateGemma), specialized in coding (QwenCode/Devstral), OCR (QwenVL), etc…

I feel that people should chill out and stop these irrational hate.
⁨Comment⁩ on ⁨I just realized there is not really a for "cuddling" in Chinese Languages... probably a reflection of the lack of Public Display of Affection in Chinese Culture...⁩ ⁨⁨1⁩ ⁨week⁩ ago⁩:
Be the change you want to see.

Create a new word for it. Spread the love in public.
⁨Comment⁩ on ⁨Apple picks Google’s Gemini AI for its big Siri upgrade⁩ ⁨⁨4⁩ ⁨weeks⁩ ago⁩:
iSlop
⁨Comment⁩ on ⁨Why You Should Never Use Pixelation To Hide Sensitive Text⁩ ⁨⁨1⁩ ⁨month⁩ ago⁩:
If the black box covers the full text, then no.

the pixel information is already gone (become black color) before it is passed to the compression algorithm.
⁨Comment⁩ on ⁨AI-generated code contains more bugs and errors than human output⁩ ⁨⁨1⁩ ⁨month⁩ ago⁩:
Because it has been like this before vibe coding existed…
⁨Comment⁩ on ⁨Immich Is Now Stable!⁩ ⁨⁨2⁩ ⁨months⁩ ago⁩:
This actually work
⁨Comment⁩ on ⁨In wake of Windows 10 retirement, over 780,000 Windows users skip Win 11 for Linux, says Zorin OS developers — distro hits unprecedented 1 million downloads in five weeks⁩ ⁨⁨2⁩ ⁨months⁩ ago⁩:
Aaaaaaaaaaaaaaaaaaaaaaaa aaaaaaaaaaa aaaaaaa
⁨Comment⁩ on ⁨In wake of Windows 10 retirement, over 780,000 Windows users skip Win 11 for Linux, says Zorin OS developers — distro hits unprecedented 1 million downloads in five weeks⁩ ⁨⁨2⁩ ⁨months⁩ ago⁩:
Everytime people say there is a problem with nvidia driver, what kind of problem do people have? I am running nvidia drivers on two different machines on arch linux. It was just pacman -Syu nvidia and thing just work

⁨Comment⁩ on ⁨Cams, anyone?⁩ ⁨⁨2⁩ ⁨months⁩ ago⁩:

Eh? Shouldn’t it be real time already?

this is my configuration:

  - camera_view: live
    type: picture-glance
    entities: []
    camera_image: camera.cam_profile000_mainstream
    tap_action:
      action: none

I am using ONVIF integration for the camera

⁨Comment⁩ on ⁨Unremovable Spyware on Samsung Devices Comes Pre-installed on Galaxy Series Devices⁩ ⁨⁨2⁩ ⁨months⁩ ago⁩:
Banking app privsec.dev/…/banking-applications-compatibility-…
⁨Comment⁩ on ⁨Google Confirms Non-ADB APK Installs Will Require Developer Registration⁩ ⁨⁨4⁩ ⁨months⁩ ago⁩:
After this you won’t be able to install it manually
⁨Comment⁩ on ⁨tool to make an stl from 2D image?⁩ ⁨⁨4⁩ ⁨months⁩ ago⁩:
also docs.comfy.org/tutorials/3d/hunyuan3D-2
⁨Comment⁩ on ⁨PNG has been updated for the first time in 22 years — new spec supports HDR and animation⁩ ⁨⁨7⁩ ⁨months⁩ ago⁩:
gif almost got replaced by mp4 anyway during the early imgur era
⁨Comment⁩ on ⁨PNG has been updated for the first time in 22 years — new spec supports HDR and animation⁩ ⁨⁨7⁩ ⁨months⁩ ago⁩:
What’s wrong with webp? It support animation, lossless compression, lossy compression and transparency. Animation has a smaller size than gif.
⁨Comment⁩ on ⁨Windows 11 is closing a loophole that let you skip making a Microsoft account⁩ ⁨⁨10⁩ ⁨months⁩ ago⁩:
I have quite a different experience, can’t tell if it is placebo or not, but my vr experience is slightly smoother in Arch Linux compared to my Windows 10.

i play VR via Proton using ALVR (steamvr) or Wivrn

But i havent tried playing Alyx on linux yet
⁨Comment⁩ on ⁨After 40 years of being free Microsoft has added a paywall to Notepad⁩ ⁨⁨11⁩ ⁨months⁩ ago⁩:
I really like my KDE plasma
⁨Comment⁩ on ⁨Jellyfin is not just good... but *better* than Plex now?!⁩ ⁨⁨11⁩ ⁨months⁩ ago⁩:
what are the things i will miss from plex’s pre-enshittification?
⁨Comment⁩ on ⁨Jellyfin is not just good... but *better* than Plex now?!⁩ ⁨⁨11⁩ ⁨months⁩ ago⁩:
it will still shows stuff in the library even if it failed to pick up the metadata.

for jellyfin, folder structure is kinda important for auto detection to work.

For shows, you can organises your files like this:
```
series-name-a/
    season-01/
      episode-01
      episode-02
```
You can check out the doc, it is more detailed