Don't jump right in to coding.

Take a feature you want, and use the plan feature to break it down. Give the plan a read. Make sure you have tests covering the files it says it'll need to touch. If not, add tests (can use LLM for that as well).

Then let the LLM work. Success rates for me are around 80% or higher for medium tasks (30 mins--1 hour for me without LLM, 15--30 mins with one, including code review)

If a task is 5 mins or so, it's usually a hit or miss (since planning would take longer). For tasks longer than 1 hour or so, it depends. Sometimes the code is full of simple idioms that the LLM can easily crush it. Other times I need to actively break it down into digestible chunks

The mouth is a small bucket so someone with a cow can milk it without issues.

PSA: don't drink raw milk, even if it's fresh and straight from the teat

No one is hoarding RAM (or DRAM aka what we call as RAM)

Instead it has mostly been a supply side crunch, and none of the individual steps are "illegal"

1. AI servers use a special memory called HBM
2. HBM is good at what it does but it has a very 'high wafer area per server' (it is stacked, and each level is lower density than normal DRAM)
3. OpenAI (and apparently others) skipped middlemen of supply chain and directly negotiated with the fab to get priority for their HBM fabrication.
4. This crunched supply on the open market for HBM
5. Other people followed up
6. Fab companies pivoted other manufacturing lines to HBM because of so many orders (and because it is really profitable to manufacture)
7. That caused crunch on DRAM
8. Other memory manufacturers pivoted to more expensive segment of their expertise (eg Flash memory fab)
9. This caused crunch on other common memory segments
10. Expensive memory means you try to move to higher segment for your own products (eg: laptop, mobile) else you don't have any slack in your BOM. This is causing the consumer good crunch
11. Once stuff becomes expensive, people hedge and buyout inventories. This is causing the Covid era style supply chain shock. The impact radius is expected to increase in coming months even if RAM situation resolves.
12. "Special mission" against Iran is blocking critical supply chain for chips (speciality chemicals, helium, etc.)

LLM seem magic if you don't have expertise in an area. Middle management and above don't have any technical expertise in their domain do they love the 40% (a bit worse than the 80-20 rule) that LLM enable.

Report: "Project is delayed because we are fixing a deadlock issue" Mgmt to LLM: "My project is delayed because of deadlock issue. What should I do?" LLM: "Oxidise your codebase and use Rust" Mgmt to team: "We should stop writing in C++ and use Rust 100%" Le Team has no rust experience and a 15 year old codebase in C++

Is it playing into the hands of Russia it was not unintended but very very intentional

It's sad to hear, but at this point those soldiers are just collateral damage. Their presence was enough to make them a target. Condemn US attacks, don't provide them with any logistical, moneyary or material support and then this whining would be a real complaint.

Email address spec is convoluted and this is indeed the best way. Noobs and ninja do it this way, normies try to validate before sending email

A credit card that only works domestically is not a deal breaker. Most of the time, people don't travel abroad. So, using a more advantageous card (more perks, less fees, etc.) domestically makes sense.

Domestic providers are a thing in several countries which are smaller than EU. Some of them don't operate internationally so this news isn't that weird

Chinese infrastructure and manufacturing lead is real. You don't need to believe any propaganda, just travel and observe.

The asterisks are not about their usecase but political.

Top 1% by wealth. Not the 1% of outliers by sexuality/gender identity

For this, bike friendly cities have good public transport (bus/tram/metro) and bike shares

Same with Switzerland