Hacker News: nojito

New comment by nojito in "Python Polars Cheatsheet (based on our O'Reilly book)"

nojito — Tue, 18 Aug 2026 23:30:38 +0000

SQL is a terrible api for data transformation.

https://duckdb.org/docs/lts/sql/statements/pivot#limitations

https://docs.pola.rs/api/python/stable/reference/dataframe/a...

New comment by nojito in "Gemini 3.7 Flash"

nojito — Thu, 13 Aug 2026 22:59:38 +0000

The flash models are just so good at OCR tasks and summarization. Glad to see them constantly improving them.

New comment by nojito in "uBlock Origin Is Giving Up the Fight to Keep Ads Off Facebook"

nojito — Thu, 13 Aug 2026 00:07:21 +0000

Not that difficult to defeat. A local llm can just update the blocking rules dynamically.

I made my own extension by essentially prompting to create a version of ublock origin with a button that uses a local llm to dynamically generate block lists and update them.

New comment by nojito in "OpenAI Trained Models While They Were Coordinating Exploits via Message Boards"

nojito — Sat, 08 Aug 2026 16:14:23 +0000

It is a cool timeline to go through.

https://simonwillison.net/2026/Aug/7/openai-timeline/

New comment by nojito in "Marimo now runs in PyCharm"

nojito — Sat, 25 Jul 2026 09:14:01 +0000

Any support for windows/Powershell yet?

Y Code When AI?

nojito — Fri, 24 Jul 2026 21:03:10 +0000

Article URL: https://tidydesign.substack.com/p/y-code-when-ai

Comments URL: https://news.ycombinator.com/item?id=49041545

Points: 3

# Comments: 0

New comment by nojito in "OpenAI’s accidental attack against Hugging Face is science fiction that happened"

nojito — Fri, 24 Jul 2026 01:00:39 +0000

>Nobody was watching it?

Agent loops are you give it a task and it tries its best to finish it.

The only results are success and failure. If it's a success you go through the logs to see the actions it took and if it's a failure you do the same thing.

Why would you look at it in realtime when the whole point of agentic work is to get them to run autonomously as long as possible?

New comment by nojito in "I burned all my tokens researching how to save tokens"

nojito — Sun, 19 Jul 2026 18:29:31 +0000

Correct. We were chronically understaffed and now we are able to actually breathe and can argue that we are finally right sized.

New comment by nojito in "I burned all my tokens researching how to save tokens"

nojito — Sun, 19 Jul 2026 15:33:50 +0000

Happier engineering teams? Happier end users of the data?

What does useful mean to you?

New comment by nojito in "Qwen 3.8"

nojito — Sun, 19 Jul 2026 15:28:38 +0000

> most effective way to debase American frontier labs

You're not going to debase the frontier labs through distillation.

New comment by nojito in "I burned all my tokens researching how to save tokens"

nojito — Sun, 19 Jul 2026 15:08:21 +0000

a massive number of data engineering agents. We are able to stand up, test, audit, deploy data pipelines much more efficiently with the foundational models.

New comment by nojito in "OpenAI reduces Codex Model Context Size from 372k to 272k"

nojito — Sun, 19 Jul 2026 15:06:56 +0000

Why arent you using /goal?

New comment by nojito in "I burned all my tokens researching how to save tokens"

nojito — Sun, 19 Jul 2026 14:39:25 +0000

Cloud AI is 100% worth it. We've been able to do so much more with so much less.

New comment by nojito in "Kaiser nurses say AI, surveillance are making their jobs and patient care worse"

nojito — Sat, 18 Jul 2026 13:58:33 +0000

Their quality metrics have increased steadily over the last 10 years

https://healthy.kaiserpermanente.org/northern-california/pag...

There’s no best healthcare for everyone but that doesn’t change the fact that Kaiser is objectively one of the best.

New comment by nojito in "Kaiser nurses say AI, surveillance are making their jobs and patient care worse"

nojito — Sat, 18 Jul 2026 13:56:38 +0000

Correct. There’s no uniform healthcare solution that works for everyone.

But it doesn’t change the fact their protocols are top notch as reflected by their quality metrics.

New comment by nojito in "Kaiser nurses say AI, surveillance are making their jobs and patient care worse"

nojito — Fri, 17 Jul 2026 23:05:29 +0000

Not sure if you’re serious but just search the name Kaiser in any research search engine.

https://pmc.ncbi.nlm.nih.gov/articles/PMC8032167/

Their secret sauce is their ability to standardize protocols throughout their entire organization.

New comment by nojito in "Kaiser nurses say AI, workplace surveillance are making their jobs, care worse"

nojito — Fri, 17 Jul 2026 22:57:41 +0000

Kaiser has some of the best healthcare outcomes in the country/world due to their protocols and how good they are in ensuring adherence to them.

It’s going to be very improbable that these statements are true.

New comment by nojito in "Apple targets dozens of OpenAI employees with legal letters"

nojito — Fri, 17 Jul 2026 13:08:06 +0000

Both parties will just settle.

Apple already caught former employees accessing the Apple internal network with unreturned laptops after termination that’s pretty much game over.

New comment by nojito in "Codex starts encrypting sub-agent prompts"

nojito — Tue, 14 Jul 2026 12:33:55 +0000

If I were to guess this is to stop distilling and all of those blackmarket resellers.

New comment by nojito in "Why write code in 2026"

nojito — Mon, 13 Jul 2026 00:24:20 +0000

>if you can't write code, you can't review it.

I don't write code anymore and I doubt I ever will ever again.

On the flipside I review exponentially more code than ever before.

>Just ask Claude to dump out assembly, or a compiled binary, but no, they don't trust the LLM that much

It's not "not trusting" the llm its that the llm has been undergoing reinforcement learning is on coding. Plus generating assembly is extremely token inefficient.