mhogers · HackerTrans

5 bulan yang laludiscuss

allowlist instead of denylist, depending on your risk profile :)

5 bulan yang laludiscuss

.agentignore/.agentnotallowed file

force agents to not touch mission critical things, fail in CI otherwise

let it work on frontends and things at the frontier of the dependency tree, where it is worth the risk

mhogers

5 bulan yang laludiscuss

but may they have their own workspace account while working with you? :)

mhogers

9 bulan yang laludiscuss

Seeing a `pip install -r requirements.txt` in a very recently created python project is almost a red flag now...

mhogers

10 bulan yang laludiscuss

Was just taking a break from reading Traefik documentation - thank you for this amazing project.

mhogers

10 bulan yang laludiscuss

I agree somewhat with you - nonetheless a FastAPI + Alembic + SQLAlchemy alternative in R would make it possible to use it as a general purpose language

mhogers

11 bulan yang laludiscuss

data layer > business logic layer > presentation layer

I believe the presentation/analytics layer has become malleable, possibly parts of the business logic layer - you still need a higher % of trustworthiness than LLMs can provide for parts of the business and data layers.

mhogers

11 bulan yang laludiscuss

Thank you for sharing, glad you are doing well now :)

mhogers

11 bulan yang laludiscuss

A 20-30 year long monthly reminder that your mortgage payments are significantly higher due to missing the boat. Ouch!

Painful for people that do not expect significant further income increases.

mhogers

12 bulan yang laludiscuss

Any reason to upgrade an M2 16GB macbook to a M4 ..GB (or 2026 M5) for local LLMs? Due an upgrade soon and perhaps it is educational to run these things more easily locally?

mhogers

tahun laludiscuss

Interesting - training for spikiness/variability is a positive view, e.g. embrace the lack of occasional sleep, it trains you to be more resilient.

mhogers

tahun laludiscuss

I had not considered the ship computer, indeed feels more close to current progress. Having said that, I started rewatching TNG recently and it is quite fascinating to compare Data to the current voice models.

mhogers

tahun laludiscuss

How close are we to building our own digital Commander Data with the current iteration of voice based agents? "In progress" according to the website - mind blowing that this is current reality.

Cool website. Would love to subscribe to status changes via email.

mhogers

tahun laludiscuss

Autogenerated interfaces from openAPI spec is so key - agents are extremely good at creating React code based on these interfaces (+ typescript + tests + lints.. for extra feedback loops etc..)

mhogers

2 tahun yang laludiscuss

Is anyone here aware of the latest research that tries to predict the outcome? Please share - super curious as well

mhogers

2 tahun yang laludiscuss

The housing crisis in The Netherlands complicates the topic in my opinion. The influx of expats should be tied closer to the available housing supply.

mhogers

2 tahun yang laludiscuss

On the async part, definitely worth checking out https://github.com/shikokuchuo/mirai, also integrates nicely with Shiny/plumber

comments