Ankit Raj (@ankit1478) header
Ankit Raj (@ankit1478) profile picture

AI Engineer | 20+ Production AI Products | 80K+ Users | Product Hunt Top 20 | Multi-Agent Systems | LLM Monitoring

Joined January 2021
Photo by Ankit Raj (@ankit1478)Photo by Ankit Raj (@ankit1478)Photo by Ankit Raj (@ankit1478)Photo by Ankit Raj (@ankit1478)Photo by Ankit Raj (@ankit1478)Photo by Ankit Raj (@ankit1478)Photo by Ankit Raj (@ankit1478)Photo by Ankit Raj (@ankit1478)Photo by Ankit Raj (@ankit1478)
Great opportunity to work with @prasad_pilla
We’re hiring an SDE Intern to join the founding team at @tryAlanAI You’ll work directly on the product across full stack features, coding agents, orchestration, cloud sandboxes, and developer infrastructure. > We don’t care much about experience. > We care if you can build. If you’ve built something you’re genuinely proud of, apply! Link in the description 👇
1
8
484
Jev
162
1,280
138
17,779
700,424
Ankit Raj retweeted
What happens between your prompt and the tokens you see on screen? 𝗔𝗻 𝗟𝗟𝗠 𝗱𝗼𝗲𝘀𝗻'𝘁 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲 𝗮𝗻 𝗮𝗻𝘀𝘄𝗲𝗿 𝗮𝗹𝗹 𝗮𝘁 𝗼𝗻𝗰𝗲. It predicts one token, appends that token to the sequence, runs the model again, predicts the next token. And keeps repeating this process. Most of us know this concept, but I wanted to understand what the inference loop actually looks like I build it myself. So I have started building a mini LLM inference engine from scratch. In this Part 1, I implemented greedy autoregressive generation: input_ids [B,T] → model forward pass → logits [B,T,V] → take the last position [B,V] → choose the highest-scoring token → append it → repeat Building such a generation loop, makes you to properly understand - what logits represent, - why the output has shape [B,T,V], - why generation only uses the last position, - and how the model's own prediction becomes the input for the next step. All this question I have tried to answer in this video in easy to understand way. This is the first part of a series Building Inference Engine where I'm progressively adding: 𝘀𝗮𝗺𝗽𝗹𝗶𝗻𝗴 → 𝗞𝗩 𝗰𝗮𝗰𝗵𝗲 → 𝗯𝗮𝘁𝗰𝗵𝗶𝗻𝗴 → 𝗽𝗮𝗱𝗱𝗶𝗻𝗴/𝗺𝗮𝘀𝗸𝘀 → 𝗧𝗧𝗙𝗧/𝗜𝗧𝗟
If you are interested in knowing how inference works, then this article is for you
2
5
1
6
502
Kill more chance
Your potential ends where your fear of judgment begins.
3
215
I got access to Jev!
5
1
18
870
Very imp to read.
We Must Pace the Frontier: I’ve written a new essay on why the AI industry should slow down, with a three-part plan for doing so. Anthropic is unilaterally committing to the first of these steps. We’ll provide third-party evaluators with permanent, employee-level access to our systems, so that they can verify adherence to our safety measures, report on incidents, and assess models’ alignment during training. You can read the full post here: darioamodei.com/post/we-must…
1
6
402
Never deleting this app #AppleEvent
19
571
This is really concerning.
I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. They are racing straight to self-improving superintelligence and gambling with our lives. More thoughts below.
1
6
713
Ankit Raj retweeted
Introducing Muse, the personal agent that understands your goals and works 24/7 to get things done for you.
3,448
2,511
2,131
36,425
8,730,777
Looking for a good whey protein under ₹3,200 Please suggest the best option you’ve personally used.
1
2
2,553
Monsoon turns my village into a living painting.
1
23
443
Ankit Raj retweeted
One thing I understood quite early in my software engineering career: Being good at coding can only get you noticed initially. But after a point, your growth depends on how well you understand business, communicate with people, take ownership and make decisions when things are unclear. And these are the core skills that later helped me build my own startup which is running successfully since 4 years now!
53
92
8
1,791
82,983
Ankit Raj retweeted
We’re introducing Claude Fable 5.1 and Claude Mythos 5.1. They're the world’s most advanced models for coding and knowledge work.
2,848
7,253
4,816
65,163
21,153,741
newton school is hiring 1 FDE intern - should be high agency - stipend will be 50k/month - on-site banglore - you will be mostly working with python, nextjs, and infrastructure related work - high ownership end to end work pls comment your PoW and resume, ill review on weekends and forward profiles
75
4
2
153
16,269
What the hell is @claudeai doing with my Max plan? With just 107K tokens, my session limit has already reached 40%, even though I’m using the Sonnet 5 model. @bcherny @ClaudeDevs
3
230
No matter what’s going on,@kirat_tw has helped me a lot. From having nothing to doing well, improving our lives, his teachings played a real part in my journey. He may be going through a tough time, but I’ll always be grateful.
3
1
103
4,669
Ankit Raj retweeted
if you're in tech and feel like you're falling behind: ◆ basically delete instagram/tiktok right now ◆ come to X very infrequently (15-20 min/day to catch up AI) ◆ actively put effort to learn something new every day stakes have never been higher to go back and be a student
112
281
21
4,943
527,364
Idempotency is very important in AI agents, especially when agents can retry tool calls automatically.
4
329
Harness engineering is basically a loop: Give task → model acts → tools run → observe result → evaluate → update context → repeat
1
6
442