From our blog

Check out our latest news and updates.

১৬ মাস ধরে এআই দিয়ে আওয়ামী লীগের পক্ষে ভুয়া খবর, গাইবান্ধার এক ব্যক্তি শনাক্ত
১৬ মাস ধরে এআই দিয়ে আওয়ামী লীগের পক্ষে ভুয়া খবর, গাইবান্ধার এক ব্যক্তি শনাক্ত
12/09/2026 — [email protected]

কৃত্রিম বুদ্ধিমত্তা (এআই) ব্যবহার করে বাংলা ভাষায় ভুয়া খবর তৈরির একটি স্বয়ংক্রিয় নেটওয়ার্ক শনাক্ত করে বন্ধ করে দিয়েছে মা...

What a large language model actually predicts
What a large language model actually predicts
12/09/2026 — [email protected]

A model does not look anything up and does not decide what is true. It estimates which token comes next. Almost everythi...

Rumeen’s remarks trigger uproar in Parliament, allegations of verbal abuse
Rumeen’s remarks trigger uproar in Parliament, allegations of verbal abuse
10/09/2026 — [email protected]

Independent member of parliament (MP) Rumeen Farhana’s remarks triggered a major uproar in the Jatiya Sangsad (national...

Tokens, not words: how a model reads your text
Tokens, not words: how a model reads your text
10/09/2026 — [email protected]

Models do not see characters or words. They see tokens — and once you know how text becomes tokens, several odd behaviou...

Embeddings explained without the linear algebra
Embeddings explained without the linear algebra
06/09/2026 — [email protected]

An embedding turns text into coordinates, and nearby coordinates mean related meaning. That single idea is what makes se...

The context window is a budget, not a memory
The context window is a budget, not a memory
02/09/2026 — [email protected]

Bigger context windows did not give models memory. They gave you a larger envelope to fill on every single request — and...

Why models hallucinate, and what actually reduces it
Why models hallucinate, and what actually reduces it
31/08/2026 — [email protected]

Hallucination is not a glitch that a better model will one day remove. It is what generation does when it has nothing to...

Giving an agent memory without giving it amnesia
Giving an agent memory without giving it amnesia
17/08/2026 — [email protected]

Memory is not a feature you enable. It is a set of decisions about what to keep, what to summarise and what to let go —...

RAG in one page: retrieve, rank, answer
RAG in one page: retrieve, rank, answer
03/08/2026 — [email protected]

Retrieval-augmented generation is three steps and a lot of tuning. The architecture is simple; the quality lives almost...

Chunking is the part of RAG nobody tunes
Chunking is the part of RAG nobody tunes
01/08/2026 — [email protected]

Teams spend weeks on rerankers and leave chunking at the default. It is usually the other way round that pays — how you...

Prompt caching: the cheapest speedup you are not using
Prompt caching: the cheapest speedup you are not using
30/07/2026 — [email protected]

If every request begins with the same two thousand tokens of instructions, you are paying full price to resend them. Ord...

The cost model of an AI feature
The cost model of an AI feature
22/07/2026 — [email protected]

Per-token pricing looks trivial until you multiply by retries, conversation history and the context you resend on every...