StarlaAtNight

Especially now that OpenAI acquired Astral

What are people actually doing with fleets of agents?

I wish every post like this had an intro section that said:

“what is {insert obscure tech thing}”

“why do people typically use {insert obscure tech thing}”

BLASPHEMY! OUT WITH YOU!

I’m now a full Mac user (personal + work), that came from Windows. Hate to say it, but Windows Explorer is better than Finder

how quick does it respond? what are specs of your laptop?

Haven’t tried it yet, but awesome work! This seems huge. I try to use DuckDB whenever feasible, and I also tend to work with Snowflake, Databricks, and BigQuery (as well as Fivetran which uses DuckDB for local dev/debug mode).

Excited to have ADBC-enabled connections w/ DuckDB, and have a feeling this is going to start coming up as a use case a lot more

This line made me chuckle. I see what you did there:

> No cookies. No tracking. No JavaScript. Real people.

I’m not sure I understand what pain point this solves. What’s the value of doing this? Is it at a certain scale?

You know what’s bad DX? Your company’s product having a massive security breach, people stop using it, and having to lay off all the software engineers

I wonder how doctors feel about people consulting ChatGPT. I know a doctor who can't stand people getting medical advice from quacks on TikTok, but that's probably a different problem/pattern

Thanks for calling that out. I went through and extracted a good handful of those. It’s not a short list. It’s a handful.

“”” The subsidy era is not winding down gracefully. It is showing cracks everywhere. … the question is not whether they got a good deal. The question is how long that deal survives. … A developer running three or four concurrent coding agents is not consuming 3x or 4x the tokens of a chat conversation. It is an order of magnitude more … These are not experiments anymore. They are load-bearing workflows. … That is not a rounding error. That is a line item that needs its own budget code. “””

I’m not very well read on the topic and you seen to take a strong “con” stance. Curious to hear why you think it deserves such a demise

Consultants or professional services folks will be working in their company’s GitHub account and several clients. Requires managing lots of git/GitHub accounts

We should be able to pin to a version of training data history like we can pin to software package versions. Release new updates w/ SemVer and let the people decide if it’s worth upgrading to

I’m sure it will get there as this space matures, but it feels like model updates are very force-fed to users