HN user

thedjpetersen

228 karma
Posts12
Comments95
View on HN

Part of my job is working on trying to make these models productive for the large corporation I work for. It's a lot of throwing tomatoes at a wall and to a degree I see the issue he is talking about output seemingly having a certain ceiling.

At the same time in no part of his post is any code snippet or anything to latch on to of "the model performed poorly here when it should have done this" - this style of criticism seems to be a pattern of most of these "the LLMs will never work" style posts on blogs and twitter.

They obviously can perform better than autocomplete and in my own day to day development build out huge portions of a codebase that I would have expected a junior or midlevel engineer to perform at.

How are we really supposed to grasp their actual capabilities when no one will actually cite specifically what mistakes they are making.

Your work (and gyroscope/stethscope/other aggregators) has inspired me to also start my own work at creating a centralized aggregator to ingest all of my data.

Why Web3? 5 years ago

Instead of unfollowing I've found that muting specific terms or words to be fairly useful at tuning the signal

Great work! The only thing is that this needs to get updated based on the changes of the new 0.9.9 release. Specifically you do not need to create a custom dispose function, remove now will remove listeners bound to the view.

Congratulations to the Grove.io team! Its great that this product is able to keep going.

I have been following Grove.io pretty closely. This is a subject that is fairly interesting to me and compelled me to look at some of the different open source options[0], as they do exist for teams that are able to run their own chat. I decided to write my own chat client with a fellow HNer called Subway[1], since I could not find a good open source web client that persisted a connection while a user was offline. After I started I found another large project that more or less accomplishes the same thing called Alice[2] written in Perl. Both these clients have more or less the same goal to persist your connection while you are offline. For those interested in a paid alternative to grove there is also IRCCloud[3] which accomplishes the same thing.

[0] http://www.thedjpetersen.com/blog/comparing_webchat_options/

[1] https://github.com/thedjpetersen/subway

[2] https://github.com/leedo/alice

[3] https://irccloud.com/

One of the collaborators here. Subway came to me as an idea a few months ago when I heard one of my co-workers trying to explain how to set up screen and IRSSI. The project has taken about 3 months to complete. There is still things to add like better IRC support and search.

A quick disclaimer the logo right now is a Gowalla Icon, this is only a placeholder I am working on designing a new logo.

I could see this becoming a popular enterprise piece of software, but most of the functionality can be glued together with jQuerys UI library or the Google Closure Widgets.

This is pretty awesome. I am very curious about language learning especially if it can be made more addictive(I have started playing with it myself http://thedjpetersen.github.com/playground/language_game/). I especially love the concept they are presenting I would like to see how they design the interface. How easy it is to go from sentence to sentence.

I have always thought that if you could simplify language learning enough and maybe add some of the addictive game elements that games like World of Warcraft have, people would not look at it as a chore but rather pour themselves into to it.