shiv.

13 posts

shiv. banner
shiv.

shiv.

@sonic_inference

Building AI for music generation & understanding. Research • Open Source • Agentic AI

Music Katılım Temmuz 2026
25 Takip Edilen8 Takipçiler
Sabitlenmiş Tweet
shiv.
shiv.@sonic_inference·
Hey, I am Shiv Let’s not go for a formal introduction. I was always into music since my class 4, and here I am , certified Indian classical musician (8+ years with 3+ years on stage experience ). But maybe I was naive or dumb, never once it came to my mind that I should pursue Music as a career, and I just saw my cousin elder brother and choose Engineering, so it was nothing dramatic for me like any passion , goal , achievement for me. And I am into engineering, I want something to do in life that keeps me connected deeply to my passion and also that I will enjoy my job much more . Now I am CSE- AIML graduate, yes I have done good-decent projects , some hackathons( both participated and organised ), in my third year I fully focused on projects (on which I fully focused ). Now I have completed DSA too, but I don’t wanna sit for on campus placements right now (unless I confirm that I have freedom to apply only to selected companies , coz I just don’t want to get selected somewhere and call it a job) Coming to this account, it will be purely a technical/professional portfolio for myself, where I would be sharing my updates of something I love working on : AI+MUSIC Yes, I just want to work in this field because I have so many delusions into this. I have also experienced some limitations to world class music models like Lyria and so many others, hope I become capable of contributing And this is all , any suggestions drop down below!
shiv. tweet media
English
3
0
5
200
shiv.
shiv.@sonic_inference·
@Pseudo_Sid26 I guess you should read Morgan Housel, and you’ll never get confused about any financial questions again
English
0
0
0
6
Siddharth
Siddharth@Pseudo_Sid26·
I have been asking myself this question from a while now- What money is enough money ?? And I realised, i cant quantify this till i full fill few checklists. When those get done, I might have a rough figure from there onwards.
English
5
0
29
855
shiv.
shiv.@sonic_inference·
@mihirss2 Thank you brother 🤞
English
0
0
0
12
shiv.
shiv.@sonic_inference·
Hey, I am Shiv Let’s not go for a formal introduction. I was always into music since my class 4, and here I am , certified Indian classical musician (8+ years with 3+ years on stage experience ). But maybe I was naive or dumb, never once it came to my mind that I should pursue Music as a career, and I just saw my cousin elder brother and choose Engineering, so it was nothing dramatic for me like any passion , goal , achievement for me. And I am into engineering, I want something to do in life that keeps me connected deeply to my passion and also that I will enjoy my job much more . Now I am CSE- AIML graduate, yes I have done good-decent projects , some hackathons( both participated and organised ), in my third year I fully focused on projects (on which I fully focused ). Now I have completed DSA too, but I don’t wanna sit for on campus placements right now (unless I confirm that I have freedom to apply only to selected companies , coz I just don’t want to get selected somewhere and call it a job) Coming to this account, it will be purely a technical/professional portfolio for myself, where I would be sharing my updates of something I love working on : AI+MUSIC Yes, I just want to work in this field because I have so many delusions into this. I have also experienced some limitations to world class music models like Lyria and so many others, hope I become capable of contributing And this is all , any suggestions drop down below!
shiv. tweet media
English
3
0
5
200
avrl ☘
avrl ☘@avrldotdev·
interviews i have failed in past 8 months: - 2x in faang - 3x in walmart - 2x in startups - 1x in investment banks mnc - 1x in expedia - 1x in oracle my success % went from 100% in 2022 to 8.3% in 2026. i am kinda enjoying this process now.
English
38
5
258
11.7K
shiv.
shiv.@sonic_inference·
@mohinitwt @solana Thank you for teaching me in simple words, although this is not my domain
English
0
0
0
4
Mohini
Mohini@mohinitwt·
--video 2-- In this vid I talked about what's actually underneath web3 i.e. the BLOCKCHAIN i hope y'all like this one as well @solana
English
5
0
7
194
shiv.
shiv.@sonic_inference·
@amaashvi Thank you aashvi 😊, wishes for your journey 🍷
English
0
0
2
19
shiv.
shiv.@sonic_inference·
@mohinitwt Thank you 😊, loving your solana series btw, keep up🤞
English
0
0
0
10
shiv.
shiv.@sonic_inference·
@xaemio Kudos, keep up the work
English
0
0
0
17
xaemio
xaemio@xaemio·
back to college. internship is over. overall it was a good experience. manager was chill. i got a great team. learned a lot. time flies so fast. back to preparing for placements and interviews. one more grind. lets see how it goes.
English
8
0
60
1K
shiv
shiv@sonic_inferenc·
@aashitwts Hey can you write a medium article or blog on this , like in an order, with the exact resources you used and also the projects you built, would be very helpful
English
1
0
0
20
Aashi
Aashi@aashitwts·
Here's more of it >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
Aashi@aashitwts

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

English
3
4
28
3.8K
Aashi
Aashi@aashitwts·
2026 AI hot take: Most ‘AI engineers’ will be prompt engineers + fine-tuners in 12-18 months.
English
10
1
18
1.6K
shiv.
shiv.@sonic_inference·
@mohinitwt great introduction , and confidence 🍻 ps: short hair looks awesome
English
1
0
1
18
Mohini
Mohini@mohinitwt·
okay this is my first vid and i was def awk but i genuinely believe in what i am saying so here we go ig ⚡ ps: yes i have short hair
English
5
1
9
209
shiv.
shiv.@sonic_inference·
@cneuralnetwork Build SonicLens, ai music understanding and discovery engine, it should listen to song , analyse melody,rhythm,tempo,timbre,mood,texture and musical similarity. Should also understand song’s musical character. Am currently working on this
English
0
0
2
19