Gaurav T

Building enterprise AI agents @Microsoft. Author of “Behind the Interface”. Built

[Gaurav T @jaguarperch]

@XFreeze What do you mean “simply talk to it”? What will you use to chat with models? How will agents spawn processes? How will they write and read from filesystem?

[Gaurav T @jaguarperch]

Agentic AI products are going to switch to Grok 4.5. It’s at least 2x faster and an order of magnitude cheaper (cheaper pricing + efficient trajectories) at the same quality as flagship models from A/ and OAI. If your company isn’t making the move, you are going to lose @SpaceXAI

[Gaurav T @jaguarperch]

Why @AnthropicAI uses @fin_ai for their own website’s chatbot? And chatbot doesn’t even use Anthropic models? Fin’s website says they use their own proprietary models. I guess SaaS not dead yet

[Gaurav T @jaguarperch]

@paraschopra I lock addictive apps. Have to dance to a hook step for 5 secs to unlock 😅. https://t.co/69aynRPo4Y

[Gaurav T @jaguarperch]

@dwarkesh_sp https://t.co/G6TCbT6VjY
Professor Robert Sedgewick- whose algorithms textbook and lectures are one of the best courses CS students can take. How does he see the future of software and computer science?

[Gaurav T @jaguarperch]

@dwarkesh_sp @reinerpope The “Behind the Interface” book explains all that in a much easier way - basically how to build a computer from silicon - one layer at a time https://t.co/J6nfgGexuc

[Gaurav T @jaguarperch]

@kimmonismus lol the reason isn’t true at all. Rather GitHub Copilot CLI is a great harness and has multi model support.

[Gaurav T @jaguarperch]

OpenAI just copied my project 😭

Sceptical about sharing your data with @OpenAI? Use PFA instead:
https://t.co/tloxEpWxsF
100% local LLM - Data stays on your device
#LocalAI #PersonalFinance

[Gaurav T @jaguarperch]

1/6 I just asked my bank accounts:
“If I cut restaurant expenses to once a month and use that for a travel fund, how many months until I can afford a 3 day Disneyland trip?”
It did the math. Across every account!
You can do this too - 100% privately. 🧵

[Gaurav T @jaguarperch]

@arjundivecha @rohanpaul_ai @adrgrondin I use it on hikes (usually have bad internet connection) to identify and learn about rocks, plants, insects etc. I use the free @get_ten_ai app as it has a lot more offline AI features - https://t.co/A5f3ccZWe2

[Gaurav T @jaguarperch]

@scootfleabag @adrgrondin MLX loads entire model in memory. Usage further peaks during a new message on already long conversation. When it crosses 4-5Gb iOS crashes app. Mobile needs to be built different. Instead try it on @get_ten_ai app which optimised for much lower memory fp (with mmap) - same speed.

[Gaurav T @jaguarperch]

@Dariton4000 @LocallyAIApp Try it on the free @get_ten_ai ios app. Gemma 4 already supported with vision and web search with citations (in agent mode). Also consumes less memory and won’t crash on long conversations. Download on App Store - https://t.co/A5f3ccZWe2

[Gaurav T @jaguarperch]

@ClementDelangue Or try it in the @get_ten_ai app on your iPhone! Compare with all the latest open source models out there

[Gaurav T @jaguarperch]

@neural_avb Open source community is 🔥 day 0 support always on MLX / llama.cpp 🥹

[Gaurav T @jaguarperch]

@ClementDelangue @huggingface Some essential things NEED local AI! For example I talk to all my bank accounts with PFA (100% on device read only agent for personal finance). Stopped paying for money management apps https://t.co/tloxEpWxsF

[Gaurav T @jaguarperch]

@neural_avb @get_ten_ai B is qwen. At least at 2B param level vision, qwen is doing better in my experience. For example here Gemma fails to say there is a bridge

[Gaurav T @jaguarperch]

@neural_avb Guess which one is Gemma 4 2B and which is qwen 3.5 2B. You can try both on the @get_ten_ai app.

[Gaurav T @jaguarperch]

@ggerganov You can also use Gemma 4 2B one on @get_ten_ai app - fast and private

[Gaurav T @jaguarperch]

Can you guess which one is @Alibaba_Qwen Qwen 3.5 2B and which one is @GoogleDeepMind Gemma 4 2B? Running locally on @get_ten_ai iOS app

[Gaurav T @jaguarperch]

6/6 It’s fully open-source and free.
GitHub 👇

https://t.co/tloxEpWxsF

⭐ Star it if you’d use this
🔁 Repost if you know someone paying for money management apps
💬 Would love contributions

[Gaurav T @jaguarperch]

1/6 I just asked my bank accounts:
“If I cut restaurant expenses to once a month and use that for a travel fund, how many months until I can afford a 3 day Disneyland trip?”
It did the math. Across every account!
You can do this too - 100% privately. 🧵

[Gaurav T @jaguarperch]

5/6 That last part is the whole point.
YNAB, Copilot, Monarch - your transactions run through their servers. You’re trusting a privacy policy.
With PFA, the AI is local. Your bank data never leaves your computer.
Not because of a promise. Because it physically can’t.