TYMorningCoffee

Joined 6 years ago

Karma
165
Submissions
98
Member since
Aug 3
josephmate.github.io
View on Hacker News

Recent submissions

Comment · 7 months ago
https://en.wikipedia.org/wiki/Pixel_Dungeon is an example of that. The bad forks dont become popular
Comment · 1 year ago
Did the grumpy gamer mean perforce instead of perform and it got auto 'corrected'?
Comment · 1 year ago
Comment · 1 year ago
Impressive! Can't wait to try Fray out at work.
Comment · 1 year ago
Click the ying yang looking icon to get an explanation

> 4-7-8 Breathing The 4-7-8 technique involves inhaling for 4 counts, holding for 7, and exhaling for 8. This pattern is repeated several times. Developed by Dr. Andrew Weil, it helps reduce anxiety, manage stress, and promote better sleep by triggering your body's natural relaxation response and slowing your heart rate.

Comment · 1 year ago
Some setups can run devstral small locally. Have you tried?

Also have you tried any other open weight models as the architect?

Third, as far as I understood, devstral was made with open hands so it might perform better there than aider out of the box.

Finally, I'm looking for local llm only setups for apple silicon 32gb and was considering devstral with open hands.

Comment · 1 year ago
A lot of commenters point out that there already are many established static checkers that do this. That is not what Uber attempts here.

Uber is not proposing a static checker. They even use sonar qube in their architecture. They propose using an LLM to resolve the leak detected by sonar qube.

Comment · 1 year ago
This architecture is promising. Large legacy code bases can have static analysis violations in the 1000s which devs never have the time to address. I've seen sonar tube reports that require man years to resolve everything.
Comment · 1 year ago
These existing tools (spotbugs, findings, sonarqube, null away, checker framework, pmd, etc) provide detection but not resolution. Resolution thru LLM is what Uber proposes.
Comment · 1 year ago
It's not identifying the leaks. In their architecture they use Sonar qube for the detecting. The LLM provides the fix.
Comment · 1 year ago
I forgot to clarify dealing with the network bottleneck
Comment · 1 year ago
Can the inference piece be partitioned over multiple hosts?

Edit: algorithmed or partitioned in a way that overcomes the network bottleneck

Comment · 1 year ago
Fixed! It was because the table overflowed. This created a scroll bar for the entire page. The entire page scrollbar had a weird interaction with the code block scroll bars. Now that there is no more whole page scroll bar, it works.
Comment · 1 year ago
I think I tracked it down to the table in the article adding a scroll bar for the entire page. This scrollbar fights with the code blocks scrollbar. I will try to refactor the table to fit in a phone width somehow.
Comment · 1 year ago
Yes. Sorry about that. Will look into it when I have time.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton