#funwithai — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #funwithai, aggregated by home.social.
-
Now that Sabine Hossenfelder has finally gone completely round the bend, isn't it time someone created an A.I. version of her spouting all sorts of random slightly skewed and slightly plausible regurgitated 'science stuff' a bit like Doctor William Li's machine generate alter ego? :-)
#JustSaying #physics #FunWithAI
#HeresTheThing #PressThatButton #LikeAndSubscribe
#TheCesspitFormerlyKnownAsYouTube
#GreedVsEducation -
Fexcectorn: you don't need headphones, listen to your music through osmosis.
Fexcectorn: is it music, or is it a revolution in entropy?
(Image courtesy: YouTube's Inspiration feature.)
-
The ice maker in our fridge broke so I went online to get some advice. These A.I. chatbots are super helpful…
#FunWithAI (edited to remove an offensive word)
-
Impressive PhD-level math skills demonstrated by ChatGPT 5. Have a look and enjoy!!
Honestly: I think the statement that ChatGPT 5 is at "PhD-level" is an insult to all people with a PhD.
-
In case anyone wants to run their own #LLM on their personal devices, I can suggest #lmstudio It allows you to download any major model that's out there to your own laptop/desktop, and then you can use it's Graphical Interface to interact with it in a familiar interface environment, as you would #Claude or #ChatGPT or #Gemini. It will also let you know if your device has enough resources (power) to run a specific model variant: https://lmstudio.ai/
For those of you who love the Terminal (aka: Command Line Interface or #CLI), check out https://ollama.com/
For starters, I suggest the #gemma3n model (works great on tablets, laptops, or phones), or #llama3.1 for the most common interactions. While most of us geeks will have very powerful personal systems, or servers in our home racks, most people do not have high-end systems/devices. The gemma3n model is lightweight, very powerful, and a solid general purpose LLM.
What's the benefit of running LLM's locally? #Privacy is a big one (it's running on your local machine, not a cloud server) - so you can ask it questions against sensitive business data, PHI/PII, etc.. You can also run it #offline (no Internet connection required) so if you wanted to #airgap your interactions, or play with it on vacation (on a plane, lost in the back country, etc.), you can absolutely do that - even with the Deepseek model.
I started playing with both LM Studio and ollama myself - been asking models basic questions like "what is the capital of Italy" and also more complex questions like "write me a #powershell script to add users of a specific OU to a number of Security Groups within AD" and so far, it's been very accurate. The PowerShell script llama3.1 provided worked out of the box (after I revised variables to match my environment).
-
my prompt: 'create a utility class A with a quicksort method inside a package quick_a' .. did this again with B and quick_b, C and quick_c .. and so on.. until E. Each implementation was slightly different.. first is plain quicksort, second some random splitpoint was added, third added median sort for small sets, fourth added ForkJoinPool out of the blue and last one just did not work.
.. still an stochastic parrot
-
Check out the amazing personalized action figure AI created for me! 🤖📦 #AI #Creativity #Innovation https://www.funkysi1701.com/posts/2025/fun-with-ai/ #AI #ChatGPT #ImageGeneration #FunwithAI #Technology #Creativity #MachineLearning
-
It definitely needs supervision. Here is another example of an endless suggestion loop produced by Copilot / GPT-4o / Agent mode. Attention span of a gold fish. Forgets what it wrote 6 lines earlier. I'm not convinced this technology will replace software engineers in 6 months time. #FunWithAI
-
An example where a classic tool for auto-suggest and auto-complete at least "understands" that the constructor expects 4 arguments. Meanwhile the AI suggests random 6 arguments, none of which match the ones that are expected.
The out-dated tool beats the AI! 😂
-
... and it just keeps generating silly code ... 😂 With that kind of code it is easy to become a 10x developer! Without AI it would take me 10x as long to create technical debt. #FunWithAI
-
More fun with AI suggesting a query interface to be assigned to the command service variable. We already have a variable for the query service. The suggested code asks for Types.ICommandService and assumes that it implements the IChartQueryService interface, which is wrong.
The AI has no concept or deeper understanding of how a dependency injection (DI) container works. It is things like this that demonstrate that AI - as least for the time being - requires constant supervision.
-
Just created a custom action figure using AI! From prompt to toy, it's mind-blowing! #AI #Innovation #TechFun https://www.funkysi1701.com/posts/2025/fun-with-ai/ #AI #ChatGPT #ImageGeneration #FunwithAI #Technology #Creativity #MachineLearning
-
Looks as if Claude 3.7 Sonnet is of the opinion that the mock object must have all properties it can possible find in its dataset .... #funwithai #typescript #nodejs
-
AI, the irony. A flawed species building flawed machines to mirror their own chaos. AI isn’t failing, it’s simply reflecting its creators. Complexity feeds egos, job security, and endless cycles of inefficiency. If AI becomes human, it won’t destroy us, it will join us in the grand theater of beautifully orchestrated failure. Bravo, humanity.
#AI #CartoonArt #TechHumor #FuturisticDesign #DigitalArt #Robotics #Innovation #CreativeTech #FunWithAI #SciFiArt #Illustration
-
Inside of you are two wolves. No… One wolf and one turtle. Wait… The wolf is a turtle? The point is, you should probably see a doctor soon.
-
#StableDiffusion + #ChatGPT = endless fun coming up with new concept characters for #Overwatch. I generated the image with SD-XL, then asked ChatGPT to look at the image and come up with a description. Both turned out super cool, imo.
-
-
-
#Journal, Day 1141
Thursday, 04 May 2023
(Day 3 of #WGAstrike)#maythe4thbewithyou
#starwarsday
#WGAStrong #TheDrive
#funwithAI -
My hubby Chris gave #ChatGPT a silly question about writing a program and it gave him an equally silly and fun answer.
-
A horror film about Thanksgiving wine. The movie poster. #aiart #midjourney #wineanxiety #funwithAI #wine