HackerLangs
TopNewTrendsCommentsPastAskShowJobs

arcanemachiner

2,605 karmajoined 4 anni fa

Submissions

The Bean is here (New "pointing stick" mouse by Ploopy)

blog.ploopy.co
5 points·by arcanemachiner·2 mesi fa·4 comments

The Inference Shift – How Cheap Chips Could Put Frontier AI in Everyone's Hands

substack.com
11 points·by arcanemachiner·3 mesi fa·3 comments

comments

arcanemachiner
·ieri·discuss
People work on different things, fail to mention their field of usage in the comments, and then misunderstand the experiences of others who do the same. Repeat ad nauseam.
arcanemachiner
·ieri·discuss
I find that I have to tell GPT and Claude to keep asking me questions, or they will just fill in the gaps themselves (wrongly).
arcanemachiner
·l’altro ieri·discuss
They also stopped making them again.
arcanemachiner
·4 giorni fa·discuss
The $5 is so they can see if open weights models are worth using, not so they can use it for a month. (Which you can't; The quota runs out way sooner than a month for any serious usage. Still worth the price of entry.)
arcanemachiner
·4 giorni fa·discuss
4.7 Flash is a small model that's almost a year old, which is ancient. And yes, your dinky GPU will not run anything worthwhile.

Just spend $5 on OpenCode Go and give GLM 5.2 a shot if you have the time. It's not quite as good as Opus, but it's more than good enough for many tasks.
arcanemachiner
·6 giorni fa·discuss
A second look is always useful when using these damn things.
arcanemachiner
·6 giorni fa·discuss
The slop is breaching temporal containment!
arcanemachiner
·8 giorni fa·discuss
Yes, and you will still not understand as well as if you had built it.
arcanemachiner
·8 giorni fa·discuss
Don't give it the necessary permissions to push to remote.

I run mine in a container, so it doesn't have access to the SSH key I use to push.
arcanemachiner
·8 giorni fa·discuss
Opus is so damn slow that it's forced me to work on multiple items at a time, whenever possible. Waiting for one session? Just switch to another!
arcanemachiner
·8 giorni fa·discuss
They didn't fork it, they post-trained on top of it.
arcanemachiner
·9 giorni fa·discuss
Sounds like you're in the Trough of Disillusionment.
arcanemachiner
·9 giorni fa·discuss
You using models released this year? I hear this complaint a lot, and it's often due to using an old model which is not as good at tool calling as newer models.
arcanemachiner
·10 giorni fa·discuss
You still have to manage/fight with the post-training that is baked into the model itself.
arcanemachiner
·10 giorni fa·discuss
Sounds like clear evidence that AI is dangerous and totally needs to be regulated, guys.
arcanemachiner
·11 giorni fa·discuss
Release date != saturation date
arcanemachiner
·11 giorni fa·discuss
We must be in different communities... Qwen models are the most recommended ones that will actually run on local hardware that is accessible to the masses!
arcanemachiner
·13 giorni fa·discuss
From what I understand, Codeberg is a pretty small nonprofit group.
arcanemachiner
·16 giorni fa·discuss
OpenCode Go is a smoking deal IMO. You basically get 6x multiplier on the $10 price since you get $60 worth of usage for $10. And the first month is only $5 so it's even better.

It goes pretty quick, but it's still a great deal. Highly recommended.
arcanemachiner
·16 giorni fa·discuss
"Nitpicking"