Allen (@Allen_George08) header
Allen (@Allen_George08) profile picture

AI Engineer | Contributor @TrenTorch | Building Reliable agents and systems that don't break.

भारत
Joined July 2024
Photo by Allen (@Allen_George08)Photo by Allen (@Allen_George08)Photo by Allen (@Allen_George08)Photo by Allen (@Allen_George08)Photo by Allen (@Allen_George08)Photo by Allen (@Allen_George08)Photo by Allen (@Allen_George08)Photo by Allen (@Allen_George08)Photo by Allen (@Allen_George08)Photo by Allen (@Allen_George08)
Hey, everyone. Benchmarked my semantic caching gateway ( on 5 models: DeepSeek Flash V4, GPT-OSS-120B, Gemini 2.5 Flash, Claude Haiku 4.5, GPT Luna Pro. p50 latency: 2.9-7.7s uncached, ~82ms on a semantic hit, ~1.4ms on an exact match. 98.5%+ lower p50. Code + benchmarks: Link in the thread:
1
4
560
Bhaiii...I lovve unexpected bangers!
1
1
37
And Indian students are grinding DSA. The oppurtunity gap is too much.
BREAKING: 600 early Anthropic employees now worth over $100 million after the IPO Over $1,000,000,000,000 wiped from stock market in past hour
33
Holy shit..
RAG is officially cooked. Researchers proved you can stuff 1 billion triple knowledge graph directly into an LLM using only 20GB of VRAM. no vector DB, no Pinecone bill, no chunking nightmares. Researchers introduced AtlasKV, and it makes the entire RAG pipeline look ancient. Instead of bolting an external search engine onto an LLM, AtlasKV integrates billion-scale knowledge graphs directly into the model's inherent attention mechanism. Using two new methods (KG2KV and HiKVP), it translates knowledge graph triples straight into the AI's internal memory with sub-linear time and memory complexity. And the numbers are ridiculous: • 1 billion knowledge triples integrated at scale • Runs on less than 20GB of GPU VRAM • Zero external retrievers • Zero bloated context windows • Zero retraining required when you add new knowledge It maintains strong grounding and generalization without paying the latency tax of searching and reading massive prompts. We spent years building clunky, fragile retrieval pipelines just to help AI look things up.
20
Allen retweeted
this is why you're further behind in your career than you think. the asymmetric information economy explained.
8
6
2
59
2,632
Allen retweeted
a reminder to not give up on your dreams
7
144
6
2,475
34,586
I am looking to be educated today. What have Indian IT Dhandos like TCS, Infosys, Wipro and the rest of the lot have actually invented apart from being sweat-shops for the west?
40
19
7
346
21,952
"There is no peace for the man who has seen what he could become.” * Epictetus
12
368
11
2,763
50,333
Okay this system design thing is hard, but I'm gonna get through it!
1
14
I am a typical tier 3 engineering student. > I say college doesn't matter, then check everyone's college on LinkedIn. > I asked @eigi_ai buddy to post this for me. (via Slack) > I tell juniors to build projects, then spend a weekend customising my terminal and reading a random book. > I say I don't care about packages, then quietly get biased for the higher LPA. > I bookmark every "roadmap to SF" thread. > I wanna leave my city. > I grind for 29 days and post my streak like it's an IPO. > I call placements a scam, then refresh the placement group 2 times a day. > I follow cracked 19-year-olds on X and feel behind every morning. > I watch a 2-hour productivity podcast instead of doing the 20-minute task. > I tell myself "trust the process." I don't know what the process is. > I own a folder full of book PDFs which I never open. > I say tier 3 doesn't define me in every intro. Including this one.
1
6
274
Kind of glowup I want. @JensenHuang can never be replaced. Period
28
Good Morning. Went to church, now wrapping up system design! No days off
6
263
Hey guys, have a look at what my brother built, and let him know what you think about it. Give it a try and support him.
launching terra a shared money pot for your group, where members decide chip in, request money, approve together, get paid. no one person holds the cash group money just got fair 🔥 Built at NEAR HACKATHON @NEARProtocol @NearBuilders #NEARHackathon > useterra.app
1
1
71
90% done with Piyush Garg System Design and covered a huge chunk on ai system design too. We move at god speed, I'm loving this subject tbh
30
I'm become genuinely happy when I see things like this: non performative,genuine, lovely people getting together.
1
45
we all owe it to Andrew Ng and 3blue1brown.
34
Conquering the world is way easier than conquering your dick.
BREAKING: Nvidia’s board officially launches investigation into CEO Jensen Huang’s relationship with Chinese spy.
1
33
Bechara, na ghar ka na ghat ka💔
China officially rejects allegations involving Nvidia CEO Jensen Huang.
32
Woke up, ate diwali barfi.. Conducted experiments for my research paper. Bike repair pe le gaya. then , nothing..Will be enjoying today with friends and family! tomorrow onwards we get back to grind.
43