We all know it's super-duper-productive and can write a lot of code in a short period of time. But I really doubt people would watch a stream on that.
289 karma · joined September 24, 2018
We all know it's super-duper-productive and can write a lot of code in a short period of time. But I really doubt people would watch a stream on that.
Even if you never read/write code anymore you still need to care. LLMs also suffer from a bad code. LLMs very quickly lose track of their own shit and start producing more bugs.
>TOP 5 METHODS FROM BORIS ON HOW TO SPEND MORE MONEY ON TOKENS
>Boris from Claude just told he doesn't prompt anymore. He LOOPS instead
>"chatgpt has gotten soooo much better with the latest update."
>"codex is the best AI coding product and we want to make it easy to try."
Karpathy about Fable 5:
>"You can give it a lot more ambitious tasks than what you're used to, the model "gets it""
Sam Altman about gpt-5.4:
>In my experience, it "gets what to do"
What a time to be alive. Models are great, but all the slop, marketing, and fakeness around them is just unbearable.
I started it a couple of years ago as personal project to help me study for interviews. Back then, it was simple RSS feed aggregator of big tech companies engineering blogs.
Recently I expanded content library to technical conferences and indie blogs, and implemented semantic search in all the library (for example, you can semantic search by all Strange Loop videos archive).
Give it a try!
https://www.phind.com/search?cache=ay8rx37gq8oy3z7uixftlqkt
https://chat.openai.com/share/a3a91dcc-a91a-4b04-8afd-40bd1a...
I have had an idea of writing Jira tasks in markdown, and then pushing them to the server via CLI. The main principle is to use Markdown levels for hierarchy, e.g:
# Epic name
## User story 1
## User story 2
### Sub task to user story 2
Maybe I will get on it again, but parsing Markdown is no-fan.
Worked for me.
Let's say I have structs:
type User struct { ID TypeID }
type Post struct { ID TypeID }
How can I ensure the correct type is used in each of the structs?
>use output from the Services to develop models that compete with OpenAI;
Well, I still can use ChatGPT labeling for many other purposes anyway.
The start was not bad and I think code was pretty good, but now I feel like lost my way at some point, and code has started degrading.
I hope when we hire new developers they will not hate me as much as I think.
Can you provide links?
Funny thing, I have seen it once on the screen of a cashbox in a supermarket in Kyiv. However, it is not clear if they really used ReactOS, or just their logo/graphics to avoid buying license for Windows.
UPD: Found the photo https://i.imgur.com/5biLbTj.jpg (2016)