Viewing profile — sreekanth850

if chunking is section aware, how do you manage large section embeddings?

Are you using blind chunking or section aware chunking?

IMHO, what is broken is retrieval, the whole blind chunking which was first generation is still the default standard in RAG, this has to be changed. I'm saying this by seeing the r…

how this can be compared against Microsoft agent framework?

The tests are based on actual expected outputs, not generated only to increase coverage. For every feature, we have a phase in TASK Ledger with scope, objective, goals and outcome.…

It took about four months. Correctness was reviewed continuously rather than only after implementation. We built the system incrementally in small slices, with humans handling the …

We (Team of 3) built a retrieval engine from scratch in .NET for investigative search, with AI doing most of the backend implementation while humans handled the design and architec…

how this compare to luna high with reduced pricing.

This is nothing but a post made by the scared CEO of a company that is now facing fierce competition from Chinese labs and losing its competitive moat, nothing more, nothing less. …

15/million. that will be much higher than subscribing claude or open AI right

how feasible its will be to run on modal or deepinfra? anyone here tried and tested such large models running?

if you can't compete, just ban them. what a clowns.

Instead of banning all LLM based repositories, they could introduce rules to discourage one shot code dumps. For example, if a repository remains inactive for more than a year, wit…

Google is walking backwards, with such a pile of cash in pocket, i feel they are doomed.

Luna respect AGENTS.md and even refuse to mark a task slice completed without testing because i wrote this as rule.

There is one thing that stay apart, I can use luna high with pretty less cost and do a comprehensive audit using sol high on every push from github.

Anthropic is losing bigtime against Open AI in coding space. I was using Claude code upto last march. Not an enterprise customer, but a responsible AI user where i don't over spend…

Future of online discussions are doomed.

AI competition, managed BY AI , discussed AI agents and commented by AI users.

looks super cool.

Bigger issue ,every app that use shadcn use 100% same. I still have to figure how people differentiate their brand using shadcn.

After using codex i will never return to cc even if they offer it for free.

Did you added auth? Last time when i checked pimary blocker was this.

I'm not an expert in fine tuning but i can obviously help if it falls under my expertise. You can shoot an email with my username and Gmail.