The initial reaction is "why on earth would I give Facebook MORE of my data, no way" but as some commenters said, this would be a great tool to use to see if it can automate some of the tools that I have not been able to automate (e.g. Facebook most of all!)
If it will help me search (or rather "comb") through rental posts on the trillions Facebook groups (that Facebook spent years making in unsearchable sanely) I have to subscribe to (just for my city) and make it even 10% better for me, I might as well pay a bit for this tool. Why? Because I like it or hate it - that's where the rental posts live (and very little elsewhere - and even those are on Facebook).
Oh the verbosity and the cryptic words that it uses. The other day, all of a sudden it used an acronym "DoD". I had no idea what it was and made me feel dumb. It's "Definition of Done". I don't care how widely used this acronym is, you just can't throw it in there.
I've now installed quite a number of tools to combat this. Just in the last few days I've installed
Look, GLM, Kimi, Deepseek and Qwen should just join forces and come up with THE model that will beat the frontier lab models even just for the benchmaxxing perspective - all just to create hype and chaos to derail the trillion IPO conversations surrounding OpenAI and Anthropic.
absolutely love forums! It's also a kind of a rite of passage for devs to create a forum if you are learning new language (back in the days) - an advanced version of "Create your first blog" type of thing?
A while back ago, I created HN Plus (hn[.]plus) (for some reason it gets blocked) - anyway, wanted to give people a way to create their own HN clone - still being used today and it was a very interesting exercise to replicate all the niche features of HN.
Hey can’t seem to DM you (probably user error) but in the world cup pickem site you built, the quarter finals are not updating. Could you look at that? Thanks!
I've signed up with Ollama to experiment with these open source models. For the past 3 months, it's just been experimenting, trying it out. GLM is the first model that I am using on a daily basis to do my coding work (as well as using Claude). It's good - I've been maxing out my Ollama usage limits everyday :)
reply