Ash Minhas

AI Content Manager @ IBM, Photographer, Thoughts are my own..

[Ash Minhas @thinkscientist]

@mikefutia YOUTUBE

[Ash Minhas @thinkscientist]

@mikefutia BANANA

[Ash Minhas @thinkscientist]

Check out my blog for a detailed description of my experience https://t.co/c2TsjcAXRz

[Ash Minhas @thinkscientist]

I used GPT-5 and Cursor to add some features to an iPhone App.

[Ash Minhas @thinkscientist]

If you live in #NewJersey and use the @PATHTrain then join the public beta here -> https://t.co/08GFi1mE0O

[Ash Minhas @thinkscientist]

Can't wait to get access to this...

[Google AI @GoogleAI]

Today we are announcing Genie 3, a general purpose world model by @GoogleDeepMind that can generate dynamic, interactive environments with a single text prompt.

World models are AI that understand facets of the world (like Veo's knowledge of intuitive physics or Genie's mastery of new environments), and serve as a key stepping stone on the path to AGI.

Genie 3 is our first world model to allow interaction in real-time, while also improving consistency and realism compared to Genie 2.

Learn more ➡️ https://t.co/dbvPn9paZm

[Ash Minhas @thinkscientist]

Had a play with Google's experiment Opal and made a kid's bedtime story generator. Looks eerily similar to tldraw in the editor.

Video sped up (2x) https://t.co/sOUxPhS3jL

[Ash Minhas @thinkscientist]

2/ Improve consistency in multi-turn conversations. Caching isn’t just a developer trick—it’s essential for scale!
Have you built with prompt caching? How much latency did you cut? #LLM #LangChain #AI #PromptEngineering

https://t.co/CPa9c3VV8g

[Ash Minhas @thinkscientist]

1/ ⚡️ Prompt caching is the unsung hero of LLM-powered apps! Instead of paying and waiting for new responses every time, cache past completions and instantly serve repeat results.

This IBM tutorial walks you through SQLiteCache:

Save on costs & Speed up your LLM App

[Ash Minhas @thinkscientist]

3/ Read all about the models on the IBM Github Page https://t.co/1uTgofqNv7

#TimeSeries #AI #Forecasting #IBMGranite

[Ash Minhas @thinkscientist]

1/ 📈 Want next-level retail demand prediction? This tutorial takes you through using a model from IBM's Time Series Foundation Model Family (TinyTimeMixer)

It's open-source, really tiny (<1M params) and performs well—no billion-parameter beast needed

https://t.co/jjkErgKnXG

[Ash Minhas @thinkscientist]

2/ It's great for for both few and zero-shot forecasting and it can easily be fine-tuned for multivariate datasets too.

[Ash Minhas @thinkscientist]

This is wild! @tldraw has blown my mind with how far down the rabbit hole their infinite canvas has got. @steveruizok gives a great demo here
https://t.co/FE7awl7zY5

[Ash Minhas @thinkscientist]

@Lane8music what was the George Fitzgerald burns remix you played last night at the Brooklyn mirage. I can’t find it! It was incredible!

[Ash Minhas @thinkscientist]

@eurydice13 @Ocado i hope theres some chocolate in the basket too :)

[Ash Minhas @thinkscientist]

@johncutlefish @swardley Would love to see what’s inside

[Ash Minhas @thinkscientist]

@allenholub No need to apologize, your expansion and articulation was spot on. Thanks for everything you share. It’s inspiring :)

[Ash Minhas @thinkscientist]

What’s the valuable outcome on each of the stories in your backlog?

[Allen Holub. https://linkedIn.com/in/allenholub @allenholub]

Stories have nothing to do with requirements. Zero. Zip. Nada. Requirements specify the desired behavior of a computer program. Stories describe the user performing a domain-level task that leads to a valuable outcome. Stories do not describe any aspect of a computer program.

[Ash Minhas @thinkscientist]

@allenholub No it was a retweet of your original with a provoking question for others. I agree with you. Teams that I lead go out and talk to users. Meet them where they are, look at what they are trying to do, then prototype and validate their understanding

[Ash Minhas @thinkscientist]

@allenholub And how do you find out what the valuable outcome is without measuring and testing? Rather than stories or requirements, why not hypothesis?