karan

I like to build cool AI agents!

[karan @karanspi]

@mmonis You also scout 1 min?

[karan @karanspi]

@NetflixIndia @netflix can you make it happen?

[karan @karanspi]

I want a movie like 12 angry men with following cast:

1) Vicky kaushal
2) Pankaj Kapur
3) Piyush mishra
4) Kumud mishra
5) Nana Patekar
6) Manoj Pahwa
7) Arshad Warsi
8) Anupam kher
9) Manish Chaudhari
10) R Madhavan
11) Jaideep Ahlawat
12) Paintal

#12angrymen #vickykaushal #bollywood #rajkumarhirani #sreeramraghavan #maheshmanjrekar #anuragkashyap #bollywood #hindimovies

[First Fellow @spluscollective]

Some stocks with the area of interest I am watching closely.

- $AVGO at 398(50ma), we are below it.
- $CLS at 50ma, 371.
- $MU at 815
- $NVDA 207-203
- $GOOGL 370
- $SNOW 240
- $MRVL 220
- $BE 265(now)

All are purely based on technical levels.

[karan @karanspi]

@TheOneLanceB @edu_trades Lance i had a great bull run but somehow lost significantly in last 3 days how to overcome that…i did proper SA took only a+ but some terrible losses triggered revenge and gave most of them!

[karan @karanspi]

You’ve got to be an idiot of a person. I watched this movie and it was amazing. The movie never had a dull moment till the end, and the acting by #TriptiiDimri and
@Madhu@MadhuriDixit was impeccable. Guys, do not listen to this guy - you will love the movie. This is coming from a reticent person like me.

[karan @karanspi]

@aaeevvyy She nailed it and so did madhuri,dharna and ravi kishan

[karan @karanspi]

@koreanoli One of the finest actresses

[karan @karanspi]

@mmonis No $NOK ?

[karan @karanspi]

Finally a fresh story with no vulgarity and copied songs and extremely impeccable acting by #triptidimri @MadhuriDixit and #dharna you all have literally nailed it … @NetflixIndia #maabehen !

[diva @divaagurlxw]

As an AI Engineer. Please learn

>Harness engineering, not just prompt engineering

>Context engineering, not just long prompts

>Prompt caching vs. semantic caching tradeoffs

>KV cache management, eviction, reuse, and memory pressure at scale

>Prefill vs. decode latency and why they optimize differently

>Continuous batching, paged attention, and throughput optimization

>Speculative decoding vs. quantization vs. distillation tradeoffs

>INT8, INT4, FP8, AWQ, GPTQ, and when quantization hurts quality

>Structured output failures, schema validation, repair loops, and fallback chains

>Function calling reliability, tool contracts, argument validation, and idempotency

>Agent guardrails, loop budgets, tool budgets, and termination conditions

>Model routing, graceful fallback logic, and degraded-mode UX

>RAG architecture: chunking, embeddings, hybrid search, reranking, and freshness

>Retrieval evals: recall, precision, grounding, attribution, and citation quality

>Evals: golden sets, regression tests, adversarial tests, LLM-as-judge, and human evals

>LLM observability as a first-class discipline: traces, spans, tokens, latency, errors, and drift

>Cost attribution per feature, workflow, tenant, and user journey not just per model

>Safety engineering: prompt injection defense, data leakage prevention, and permission boundaries

>Multi-tenant isolation, cache safety, and cross-user context contamination prevention

>Fine-tuning vs. in-context learning vs. RAG vs. distillation and when each is the wrong tool

>Latency, quality, cost, and reliability tradeoffs across the full inference stack

>Production failure modes: hallucinated tool calls, malformed JSON, stale retrieval, runaway agents, and silent eval regressions

[aditya @adxtyahq]

for anyone asking where to learn this stuff:

• RAG → https://t.co/4bzbUIwV5g
• Agentic RAG → https://t.co/IotOiGmV1Y
• AI Agents → https://t.co/nEeMnVJQbk
• Multi-Agent Systems → https://t.co/pavDPVJEFj
• LangGraph → https://t.co/3miEqqFzF0
• LangGraph (code) → https://t.co/v7kxHZXqba
• MCP → https://t.co/lKawRb4etX
• Memory Systems → https://t.co/LSaT2UaPAS
• Evals → https://t.co/vxChxa1kqQ
• Context Engineering → search "Context Engineering Survey" on arXiv

and please skip the "build an ai agent in 10 minutes" videos
build something, watch it fail, then figure out why.

[Rohit Kumar Tiwari @_rohit_tiwari_]

AI Engineering from Scratch.

503 lessons. 20 phases. 320 hours.

https://t.co/UuX9N62VCU

Phase 00: Setup & Tooling (12 lessons)
Phase 01: Math Foundations (22 lessons)
Phase 02: ML Fundamentals (18 lessons)
Phase 03: Deep Learning Core (13 lessons)
Phase 04: Computer Vision (28 lessons)
Phase 05: NLP (29 lessons)
Phase 06: Speech & Audio (17 lessons)
Phase 07: Transformers Deep Dive (14 lessons)
Phase 08: Generative AI (14 lessons)
Phase 09: Reinforcement Learning (12 lessons)
Phase 10: LLMs from Scratch (22 lessons)
Phase 11: LLM Engineering (15 lessons)
Phase 12: Multimodal AI (25 lessons)
Phase 13: Tools & Protocols (23 lessons)
Phase 14: Agent Engineering (42 lessons)
Phase 15: Autonomous Systems (22 lessons)
Phase 16: Multi-Agent & Swarms (25 lessons)
Phase 17: Infrastructure & Production (28 lessons)
Phase 18: Ethics, Safety & Alignment (30 lessons)
Phase 19: Capstone Projects (85 lessons)

[francesco rosciano @frank__rosh]

Call +1 (920) 7-PATTER.

Hear an AI phone agent answer in 412 ms.

Open-source SDK. MIT licensed.

[Sean Matthew @_sean_matthew]

So many good recommendations here, and I would've never thought of #3 (despite using compound engineering all the time).

[karan @karanspi]

Are these the two best questions a trader should ask:

1) Is there a setup?
2) What is stop loss?

[karan @karanspi]

@mmonis @ShakePryzby1 Quick question bm says 150 level stronger then why you got in at 154?

[karan @karanspi]

@AyushiiDoshiii One word civic sense !

[winkle. @w1nklerr]

Nvidia will now pay you to put a mini AI data center on your house

It looks like a normal AC unit in the yard.

But inside sits 16 Nvidia Blackwell GPUs and Dell servers.

A startup called Span builds them, backed by Nvidia.

They bolt onto your home and you get paid for the power and Wi-Fi.

Some estimates put that around $1,000 a month in your pocket.

That is rent money just for hosting a box outside.

Span says it deploys way faster and cheaper than a real data center.

The AI boom is literally moving into the suburbs.

Save this, the grid is getting rebuilt in real time.

[karan @karanspi]

@elonmusk @ericmetaxas Remember the dialogue from his film :

“ You either die a hero or live long enough to become a villain”.