sacha

structured data analysis from first principles @retabdev // shadcn high priest // prev @polytechnique, physics PhD

[Hunter Leath @jhleath]

it remains super odd to me that none of the existing agent frameworks, Mastra, Flue, or now Eve seem to do anything about getting context into the agent?

every team that i talk to who are designing agents at-scale need to figure out how to get the enterprise data *to* the agent, which requires carefully planning ETL, evaluating how well the agent performs with different data formats, running things like map-reduce

and yet, every one of the agent frameworks just... leaves this to user with no opinion on it?

maybe you can only do this part with a fully-owned storage layer, idk

[Josiah Lippincott @jlippincott]

The world is full of losers. The only reason anything good happens is because dreamers work to make reality better.

[sacha @sachaicb]

@_philschmid Choose co-design sir

[Marc Andreessen 🇺🇸 @pmarca]

Many people are saying.

[sacha @sachaicb]

It’s time to reconsider this

[typedfemale @typedfemale]

> "at google we" let me stop you right there. because you aren't at google. not even close. everything you did "at google" was a sick perversion of our ideals. we will not allow it here. bring up bazel again and your coworkers have been instructed to attack you with baseball bats

[Elad Gil @eladgil]

The events of the last 6 months in technology are arguable amongst the most important in human history

The tools now increasingly exist for recursive self improvement of models & agents

We are likely in very early lift off & exponential

Largely unnoticed outside of tech

[Raphael Schaad @raphaelschaad]

I’m a sucker for good names.

Legora > Harvey
Polymarket > Kalshi

And it’s not even close. It obviously doesn’t make or break a company (Google), but a good name is a great asset when competing for category domination.

[sacha @sachaicb]

@samlambert Good engineers also care about leverage

[Dylan Field @zoink]

@DamiDina Yes. While 5.5 over-complicates some tasks, and doesn't excel in all domains, it is overall excellent.

IMO the "model as tool" path is a better direction than "model as persona" path. And (hot take) I worry the "model as persona" path + Ant's post training is an AI safety risk.

[sacha @sachaicb]

@joannejang ssi

[sacha @sachaicb]

@karrisaarinen Red queen races

[kache @yacineMTB]

https://t.co/bpI7scnxRO

[le.hl @0xleegenz]

Team meeting after the entire HR team got fired

[Uncle Bob Martin @unclebobmartin]

I am absolutely more productive using agents. I don't know the factor but it's large. However much of that productivity is spent tuning the agents and hardening the product. I'm guessing 30%-40%.

Some might consider that a waste; but I don't. The software I'm creating nowadays is vastly more robust than I'd ever been able to create manually.

I don't mean that the code is better. I mean the surrounding tests are vastly better. I have a higher degree of confidence than I ever had manually -- even when I used very disciplined TDD and Acceptance testing.

And then there's the ability to quickly reorganize the modules and the architecture while keeping those robust tests running. That is a tremendous boon.

[Sam Altman @sama]

a general-purpose model solved a major open problem in mathematics.

we'll be saying this a lot over the coming years, but this is a kinda big milestone.

i'm very excited for AI to greatly extend our understanding of the world, but still, i have complicated feelings today.

[Atelier Missor @AtelierMissor_]

French people judge Napoleon by ridiculous metrics and say France was in worse shape after him. They don’t understand.

Do you take into account that he taught audacity to millions? Do you imagine the economic implications?

For France to become epic again, we have to admire our great hero.

[Elon Musk @elonmusk]

True

[kache @yacineMTB]

It's so depressing when you finish a project man. Or hit a technical milestone. God damn it