← Feed

Posts

• Post #4313389

  I know it's nothing new, but I'm still gonna say it: why do people use LLMs for coding? I have access to LLMs at work, so from time to time I test them (different models, different problems), but almost every time they return garbage code. - Recently I asked it to write code and avoid a specific pattern that was introducing a security vulnerability. The LLM insisting on the pattern and re-introducing it multiple times, even if reminded that it should not. - In other case, it sug...

• Post #4313388

  I was listening to an interview with an American socialist. He was talking about a socialist agenda for the US and… he was basically describing Europe.

• Post #1764611

  - I will close the Strait of Hormuz! - No, I will! - I will!!! - It’s closed by me right now! - No, it is not, I am closing it! … https://www.nytimes.com/2026/04/27/us/trump-iran-proposal.html?unlocked_article_code=1.eVA.0vfu.000aVH8DhanP&smid=url-share

• Post #1736280

  Can we agree that we already reached the peak of the hype cycle, or do we need people to still keep trying..?

• Post #1736279

  Why there’s no very complex numbers like -5 + (4 + 8i)j ?

• Post #1736278

  „Slopaganda” 🥹 https://www.nytimes.com/interactive/2026/04/25/business/iran-trump-israel-war-memes.html?unlocked_article_code=1.dlA.ImNo.Bfu4FyK7wxNG&smid=url-share

• Post #1736276

  Yeah, it's a pissing competition... https://www.nytimes.com/2026/04/26/business/artificial-intelligence-energy-data-centers.html?unlocked_article_code=1.eFA.D8X8.dtrf7KypT8Wy&smid=url-share

• Post #1736275

  There should be a 💩 emoji reaction on LinkedIn. It would totally boost engagement metrics.

• Post #1736274

  RE: https://masto.ai/@phoronix/116476120066302561 Open-source enshittification is technically a diarrhea..?

• Post #1088773

  Great business model: AI writes a code with a bug ($), than reviews it ($), fixes ($), and reviews again ($). Full-stack billing 😆 https://aiworld.eu/story/code-review-and-the-end-of-subsidized-tokens

• Post #772527

  LLM "productivity"

• Post #649285

  I was always finding #regex engines intriguing and maybe a bit intimidating, so I decided to implement my own in #rust to understand better how they work. It implements the basic features (grep-like) and the implementation aims rather at clarity than performance (it is not slow, though). It was surprisingly easy to implement and much simpler than I'd imagine, so an interesting journey. I left some more details in README. https://github.com/twolodzko/t-rex

• Post #377503

  https://www.engadget.com/ai/13-hour-aws-outage-reportedly-caused-by-amazons-own-ai-tools-170930190.html