Hacker Newsnew | past | comments | ask | show | jobs | submit | freddref's commentslogin

We might finally now attain the engineering practice and discipline we've always wanted, without distractions. In some ways we're now forced to engineer in a more rigorous way to deal with the deluge of code, and ensure something high quality comes out the other end of the process.

Very nice, I've had great experience using hn to recommend, more like a feed though: https://xiliary.com/bck/hn-tv.html


You have to ruthlessly prune the feed to get something worth reading.


What are these bottlenecks specifically that you feel are essential?

Am trying to compare this to reports that people are not reviewing code any more.


When features and their exact UI implementations are being developed, feedback and discussions around those things.


https://batsign.me

The world's simplest personal Email notification API.


Definitely feels like a good amount of dev work is writing the same things over and over, in a different language, codebase or context. And it seems like llms are particularly good at translating, specializing and contextualizing across existing knowledge.


It might be financial beneficial once as an up-front payment, but long term, as others have mentioned, really not good for the project to remove the only feature that gives firefox a defensible way to fill it's niche in the market.


That wouldn’t seem so much out of the ordinary, long-term thinking CEO is an oxymoron these days.


How is Devin different from cursor?

I recently used cursor and it has felt very capable in implementing tasks across files. I get that cursor is an IDE but it's ai functionality feels very agentic.. where do you draw the line?


Cursor Composer (both "normal" and "agent" mode) fit the colloquial definition of agent, for sure.


I had to look up MCST: it means Model-Centric Software Tools, as opposed to autonomous agents.

Devin is closer to a long-running process that you can interact with as it is processing tasks, whereas Cursor is closer to a function call: once you've made the call, the only think you can do is wait for the result.


It stands for Monte Carlo search tree.

Ie. Better outputs from models, not external tooling and prompt engineering.

https://github.com/zz1358m/MCTS-AHD-master


Thanks for the correction, I guess I was lured by yet another LLM confabulation


Two lads set themselves up in the business of selling conkers one year.

Any accidentally dropped conkers were stamped on by any and all in the vicinity.

A conker that survived to the next year was considered "seasoned", although many's the wizened tippex-covered lump of questionable provenance appeared under this explanation.


Any stats available on accuracy?


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: