sujoy

⚡️

[sujoy @chuphojasujoy]

text your ex, life is too short to re-construct a relationship from scratch

[Bhupesh @bhupeshnegi_]

beetle on a fujifilm

📍halasuru, blr

[sujoy @chuphojasujoy]

Best birthday ngl

[Bhupesh @bhupeshnegi_]

went for a photowalk

📍commercial street, blr
📸 fuji xs20

will share more shots soon…

[amirtha @ewyuckugh]

if i hear one more restaurant/bar/cafe suggestion i WILL scream. do yall not like going to ur friends’ houses…

[sujoy @chuphojasujoy]

Hiring in my team at Gushwork.
Associate Program Manager on our website development product.

Think Lovable, but for B2B SMBs. Our AI pipeline (Onboarding Studio) takes a domain to a live site in 30 minutes. You own the loop from customer call to shipped website: steer the pipeline, feed it what it's missing, and ship what it can't.

Manage ops + tech.

Bangalore. Startup pace.

Bar: 1-2 years at an early-stage startup. Steps into the code and knows their shit in Claude Code. Turns a messy customer call into 5 clean lines of spec.

Read the JD before you DM. Been filtering hard.
https://t.co/Mi6kND64pV

#hiring

[sujoy @chuphojasujoy]

arey tanisha green flag

[Tanisha Sharma @tanishasharmax]

@Ayussheth home AI a fridge bot that sees the stuff i have and suggests what to buy in terms of groceries

[sujoy @chuphojasujoy]

@tanishasharmax @bolna_dev @bhupeshnegi_ @luvbansall let's do this

[sujoy @chuphojasujoy]

Wispr Flow final boss

[Luv Bansal @luvbansall]

Every HYROX athlete has two jobs:

- Training for HYROX
- Explaining what HYROX is to all non-athletes friends

[Tanisha Sharma @tanishasharmax]

fablemaxxxxing

[djcows @djcows]

BREAKING: Haaland has joined Anthropic as Member of Technical Staff

[Luv Bansal @luvbansall]

LLMs are still slow because they generate one token at a time.

That is the bottleneck DFlash tries to attack.

I wrote a blog breaking down **DFlash: Block Diffusion for Flash Speculative Decoding**.

The main idea:

Instead of drafting future tokens one by one, DFlash uses a block diffusion drafter to predict multiple future tokens in parallel, then lets the target LLM verify them.

In the post, I covered:

* speculative decoding basics
* why draft models can still be sequential bottlenecks
* block diffusion drafting
* target hidden features
* KV injection
* reported `6x` lossless acceleration

[Luv Bansal @luvbansall]

I haven’t posted much here or written blogs in a while.
Trying to change that now.

I’ve been reading more AI research papers recently, especially around LLM inference, optimization, serving systems, and model efficiency.

Instead of just keeping notes for myself, I want to turn more of them into blogs.

The plan is simple:
- read papers more regularly
- write practical breakdowns
- focus on intuition, implementation, and tradeoffs
- post on both Substack and Medium

If you’re interested in AI research, LLM systems, and ML engineering, follow along.

Substack: https://t.co/x6ZRoaDGAn
Medium: https://t.co/AQTAH0IFvn
#AI #MachineLearning #LLM #DeepLearning #GenAI

[Bhupesh @bhupeshnegi_]

sunday run party 🏃‍♂️

[sujoy @chuphojasujoy]

me when any minor inconvenience

[bandita @ridiculoussshe]

breakup so bad i start thinking about mba

[sujoy @chuphojasujoy]

@tanishasharmax @sonumbonweb @bhupeshnegi_ @bansal22luvi in

[gaut @0xgaut]

sorry babe I can’t tonight Fable is back

[sushi @tandoorinightts]

sent a mail starting with ‘Sure, here’s a more polished and professional version of your message’ now where do i hide from the face of this earth this is too embarrassing

[sujoy @chuphojasujoy]

@janhviiiieeee us