pull down to refresh

@tonyaldon
stacking since: #110937
bio
221 items
by
for
Learning requires inefficiency - Let AI show you what you don't knowtonyaldon.com/2026-02-21-learning-requires-inefficiency/
160 sats \ 0 comments \ @tonyaldon 21 Feb AI
How to improve the Python import time of your Typer CLItonyaldon.com/2026-02-17-how-to-improve-the-python-import-time-of-your-typer-cli/
50 sats \ 0 comments \ @tonyaldon 17 Feb devs
How I generated Python test data with LLMstonyaldon.com/2026-02-16-how-i-generated-python-test-data-with-llms/
190 sats \ 0 comments \ @tonyaldon 16 Feb AI
OpenAI API and structured logging in Pythontonyaldon.com/2026-02-15-openai-api-and-structured-logging-in-python/
190 sats \ 0 comments \ @tonyaldon 15 Feb AI
145 sats \ 2 replies \ @tonyaldon OP 14 Feb \ parent \ on: Simple, short and correct AI

Two really different realities I guess! You must be learning a lot in that space. Is the gap big? Or is it just fine to work with smaller local models?

145 sats \ 4 replies \ @tonyaldon OP 14 Feb \ parent \ on: Simple, short and correct AI

Simplicity.

I pick one tool, it works and gets the job done. I stick with it. I never think of it ever. Done. The cost of switching tool is too high. And I treat LLM models the same as a text editor, a library. And the good one are just fine.

Further more, I don't need a .5 improvement on a model which doesn't help me much if I don't get a .5 improvement on my brain too.

What's your take on this? Do you often switch models and tooling around these models?

145 sats \ 0 replies \ @tonyaldon OP 14 Feb \ parent \ on: Simple, short and correct AI

Here's a great talk about simplicity by Rich Hickey the author of the clojure language. Highly recommended 👌

145 sats \ 6 replies \ @tonyaldon OP 14 Feb \ parent \ on: Simple, short and correct AI

I have no idea. I don't follow much LLM rankings. I always use the latest best OpenAI model (from their API) and try to get the most out of it.

Simple, short and correcttonyaldon.com/2026-02-14-simple-short-and-correct/
290 sats \ 10 comments \ @tonyaldon 14 Feb AI
Logging requests when the OpenAI API errors in Pythontonyaldon.com/2026-02-13-logging-requests-when-the-openai-api-errors-in-python/
190 sats \ 0 comments \ @tonyaldon 13 Feb AI
Mocking the OpenAI API with respx in Pythontonyaldon.com/2026-02-12-mocking-the-openai-api-with-respx-in-python/
256 sats \ 2 comments \ @tonyaldon 12 Feb AI
128k whitespace tokens, by accident: debugging the Responses APItonyaldon.com/2026-02-11-128k-whitespace-tokens-by-accident-debugging-the-responses-api/
393 sats \ 2 comments \ @tonyaldon 11 Feb AI
1 sat \ 0 replies \ @tonyaldon OP 7 Feb \ parent \ on: Tech improvements are quickly taken for granted AI

Benefit/cost is real, totally agreed with you.

1 sat \ 2 replies \ @tonyaldon OP 7 Feb \ parent \ on: Tech improvements are quickly taken for granted AI

What do you mean by?

Especially as people feel they can vibe code anything they hear about
Tech improvements are quickly taken for grantedtonyaldon.com/2026-02-07-tech-improvements-are-quickly-taken-for-granted/
237 sats \ 4 comments \ @tonyaldon 7 Feb AI
I made a CLI to enrich Fr-En phrasebooks with AI translations, audio, and imagestonyaldon.com/2026-02-06-i-made-a-cli-to-enrich-french-english-phrasebooks-with-ai-translations-audios-and-images/
152 sats \ 0 comments \ @tonyaldon 6 Feb AI
Cut through the noisetonyaldon.com/2026-01-31-cut-through-the-noise/
172 sats \ 0 comments \ @tonyaldon 31 Jan AI
101 sats \ 0 replies \ @tonyaldon OP 24 Jan \ parent \ on: AI killed traditional learning AI

I like it too. That's how I feel about AI chats righ now.