Uday (@udayj) 's Twitter Profile
Uday

@udayj

Solidity | Cairo | Rust
Building on Starknet by @StarkWareLtd - All views strictly personal

ID: 19435402

linkhttps://github.com/udayj calendar_today24-01-2009 07:49:57

146 Tweet

196 Followers

629 Following

Uday (@udayj) 's Twitter Profile Photo

I've found LLMs to be quite good at converting imprecise user instructions to precise in-code actions - I think this will turn out to be a very fruitful application design pattern for enabling new use-cases by reusing existing interfaces to reduce user-onboarding friction

Uday (@udayj) 's Twitter Profile Photo

Getting recommended by LLMs - with proper context and reasoning - is going to be the next evolution in SEO - in effect, this is compressing all the wisdom of the crowd and giving you true crowd sourced review on a topic - Claude recommending twilio alternatives here

Getting recommended by LLMs - with proper context and reasoning - is going to be the next evolution in SEO - in effect, this is compressing all the wisdom of the crowd and giving you true crowd sourced review on a topic - <a href="/claudeai/">Claude</a> recommending <a href="/twilio/">twilio</a> alternatives here
Uday (@udayj) 's Twitter Profile Photo

The time required to get something to work on Telegram Messenger v/s WhatsApp API is astounding - WhatsApp still has much bigger distribution but Telegram devX beats it everyday of the week - approvals on WhatsApp can be an indefinite wait with no feedback

Uday (@udayj) 's Twitter Profile Photo

Contrarian view - Custom UIs for every use case add complexity & training for users. Chat/voice interfaces are familiar, simple & effective for most AI apps - of course, caveats apply - let users talk, type or show if possible - its much easier

Uday (@udayj) 's Twitter Profile Photo

Knowing the limits of what you can do with AI is going to be crucial in designing useful systems - technical knowhow is going to be as important as domain expertise - its context engineering and not just context

Uday (@udayj) 's Twitter Profile Photo

💯 Agree - and there is a related point to this - you can vibe code your way to a demo but much more difficult to create a cross-functional, maintainable, deployable system that integrates into existing workflows and provides sustainable value - this is the opportunity I think

Uday (@udayj) 's Twitter Profile Photo

While Claude has become quite good at following examples and generating structured output, extracting text from images is still not its forte - had to resort to Amazon Textract Amazon Web Services for OCR which has delivered much better accuracy - an example where AI is not better than

Uday (@udayj) 's Twitter Profile Photo

openai/gpt-oss-120b is surprisingly strong at converting natural language instruction to structured JSON compared to tool calling accuracy especially for deeply nested input schemas

Uday (@udayj) 's Twitter Profile Photo

Chat or messenger type UXs are an incredible form factor for getting started with agentic systems - there is almost no learning curve involved - domain experts can simply level up as power users without the friction of mastering a new and constantly updating interface

Uday (@udayj) 's Twitter Profile Photo

I think Starknet (BTCFi arc) 🥷’s infra is top-tier—fast, scalable, secure. But it needs its “Excel moment”: a game-changing app that’s sticky & iconic, driving adoption like Excel did for Windows. What app could do this?

Uday (@udayj) 's Twitter Profile Photo

Not every "guess" in data processing is a hallucination. In raw images from any digital camera - be it a DSLR or smartphone - each pixel captures just one color through a filter (like in Bayer arrays), so about 2/3 of the color data is interpolated from neighbors. I would call

Uday (@udayj) 's Twitter Profile Photo

Prompt optimization is a fragile process, but GEPA and DSPy continue to amaze me with remarkable results - turning a manual brittle process into robust engineering through reflection based prompt optimization - got almost ~30% latency reduction by teaching

Uday (@udayj) 's Twitter Profile Photo

Compute isn't the real bottleneck - shortage of talent at the intersection of domain expertise, knowing what can be built and knowing how to build it is - this is where magical experiences get created

Uday (@udayj) 's Twitter Profile Photo

Success of coding agents like Claude Code and Cursor like IDEs just proves this point - these products have all the 3 ingredients to make it work - it just turns out that people with the domain expertise here are programmers themselves who not only know what can be built but also

Uday (@udayj) 's Twitter Profile Photo

I am no thought leader, but what vitalik.eth has been saying recently as well as Eli Ben-Sasson | Starknet.io is imo a good reset of the north star - its asking the same question as the quoted tweet but of the base blockchain/L2 itself instead of the application teams - a good number of

Uday (@udayj) 's Twitter Profile Photo

Counter-intuitive at first, but now obvious in practice: Asking Claude Code to write code for an analysis task usually beats asking it to just do the analysis directly - often by a lot. Real example: Client had transaction ledgers split by location in a dozen separate PDFs.

Uday (@udayj) 's Twitter Profile Photo

Retrofitting existing ERPs and legacy systems with modern interfaces and tools is more likely to get a buy-in from institutions than a full rewrite from scratch ever will - irrespective of how easy it is with agent swarms. While there is an astounding hype around how enterprises