laxman

20 | It is our moral obligation to make an impact in the world proportionate to our potential | shippin @vektorimemory prev: cognitivelab, bhindiai(upsurgelabs)

[laxman @llmluthor]

We built an AI that remembers like a brain, not a database.

Vektori builds a living graph of every conversation you've ever had. Fresh concepts glow bright. Old ones fade, unless you reinforce them.

20+ daily users trusting us with their entire digital memory.

No venture backing. Just pure engineering spite :)

[laxman @llmluthor]

@IterIntellectus i thought post agi, tourism industry will boom but 😭

[laxman @llmluthor]

@niveditjain Dmed

[laxman @llmluthor]

build things that are genuinely hard and real, work at the frontier, be the person with conviction who bets early.

[Paul Graham @paulg]

If big companies can't make a net return on their LLM token costs, that doesn't mean it's impossible to. In fact this is exactly what you'd expect to happen with a new technology. Incumbents can't use it well, and are replaced by upstarts who can.

[laxman @llmluthor]

It was never the sea. It was one bend in the river.

[laxman @llmluthor]

Policy is an object, execution is art

[laxman @llmluthor]

@HCL250202 Maybe just misogyny honestly :(

[Harj Taggar @harjtaggar]

Real product-market fit is customers absorbing risk to use you because the pain is that bad. “We'd need to see more customers first” means you don't have it.

[laxman @llmluthor]

@DbrxMosaicAI so similar to RLMs approach?

[laxman @llmluthor]

@xdotli series would be 🔥, would love to know in depth

[laxman @llmluthor]

Yahoo moment openai?

[Andrej Karpathy @karpathy]

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

[laxman @llmluthor]

@karpathy @sama

[laxman @llmluthor]

@alexabelonix yes, one of the simpler yet effective ways to deal with context rot

[laxman @llmluthor]

LLM context is broken. Attention degradation completely destroys context over massive data.

The fix?

Augmenting transformers with explicit semantic
tagging using tools like the TAGME algorithm.

By injecting structured metadata into the prompt.

[laxman @llmluthor]

https://t.co/JtUVUuH82L

[laxman @llmluthor]

@sama

[laxman @llmluthor]

Don’t chase status.  Status without substance doesn’t work for long and is unfulfilling.

[laxman @llmluthor]

Context Window - Context window is specified by a number and the direction.