Siddharth (@pseudo_sid26) — sponsored posts & rates

@pseudo_sid26

Siddharth5.5K

Siddharth

This creator added themselves. Not verified by unfair.so.

@pseudo_sid26AI AgentsMachine LearningAI Engineering

5.5KFollowers

1.5KMedian impr. / post

1.8%Engagement

Paid partnerships

In their audience

6 affiliated with @amazon follow Siddharth

@ankushdharkar

@HelloVyom

@_Shiva_iitp

@build_with_abhi

@gannik__

@vihaaan17

6 from @ycombinator

5 affiliated with @google

4 affiliated with @mem0ai

4 affiliated with @superteamin

4 affiliated with @microsoft

905 verified followers analyzed

@ankushdharkar

@HelloVyom

@_Shiva_iitp

@build_with_abhi

@gannik__

@vihaaan17+899121 AI engineers89 engineers61 AI founders54 founders39 AI researchers32 devtools engineers

18–24 core age group

43.9%

55% of audience in India

🇮🇳

Aug 29 – Sep 4129 posts analyzed · replies not counted · updates weekly

ImpressionsEngagements

21.6K10.8K0

7803900

Aug 29Aug 30Aug 31Sep 1Sep 2Sep 3Sep 4

Past collabs

Siddharth@pseudo_sid26 · Sep 3I use Claude and Codex models pretty heavily for work. When I build applications, I usually reach for OpenAI, Anthropic, or even Gemini APIs sometime for low balled tasks xd. The problem is that managing multiple providers gets too big of a task alone - >Different API keys.  >Different billing/recharges.  >Different SDKs.  >And if you're following Hexagonal Architecture for agents like me, another adapter for every provider. I recently tried Distokens to solve this provider + cost + memory + build problem. The architecture changed quite a bit: > One adapter in my agent architecture instead of one per LLM provider. > OpenAI Agents SDK everywhere, while Distokens handles the model providers underneath. > Task-based provider selection, so I can use the right model for the job instead of defaulting everything to the most expensive one. > Persistent agent state during development. I'm saving work summary where supported and agent memory in .md files ( using my cerebra - brain styled memory system underneath hehe ). So when I switch providers, the next model doesn't have to start completely from scratch. It can pick up from the state I've persisted. And for agentic workflows, it makes running REACT/OODA-style loops a lot more practical without burning through expensive models on every step. Definitely worth it for me, do give it a try, sign up via my referral link and get $20 worth of credits for freeeeeeeee - https://distokens.com/register?promo=siddharth01

DistokensPaid partnership1.3K views

Siddharth@pseudo_sid26 · Mar 283 terminals 3 agents 3 different models That's blackbox cli for you. I had an application made on html with jinja template with css and ajax and sq lite db. Obviously this tech stack was very basic, so I thought of improving the tech stack to take this to scale. Used minimax in one TUI for frontend optimization Used codex to effectively switch to local postgres on docker. Used opus in another terminal for backend and celery jobs optimization. The app turned out well with react, although I still need to do some changes in frontend and need to fix some new endpoints but this multi-cli-multi-agent setup just left right here !! PS - Music in bg is made by me only, I use my own music only lol

BlackboxPaid partnership1.3K views

Siddharth@pseudo_sid26 · Mar 14I got the early access to CodeHelp platform. Here's what my first impression looked like after doom testing it - >the interactive roadmap feature is insane >article section covers very niche topics with code snippets as well. >the interactive game mode for CSS learning is a killer feature. since its in beta, the overall UI isn't very smooth and responsive but I believe they will improve it. other than that, the AI coach/AI assistant could actually be used in a better way to maybe interact with the articles or the course content in general. this AI coach/chatbot could actually be used to generate personalized weekly summaries of topics where student did a series of recursive questions or topics where student was sort of confused and took the help of the bot to understand things. We can later ping them to revise these topics on weekly or even monthly basis the interview section isn't live yet but i am excited for it. overall this could be a very good platform tbvh.

CodehelpPaid partnership866 views

Planning a launch?Siddharth is one of 200 curated B2B creators. Tell us what you are launching and we will put the shortlist together.

[email protected]·t.me/fdrtrm

1 picked$100