I agree that current memory systems are pretty bad, and I think that’s because memory is a prompted behavior instead of a learned one. In theory, if memory was an emergent behavior instead of a prompted one, it would be a lot better.
I think you’re right that changing its own harness would be bad and skew towards prompt engineering instead of learned behavior. So maybe instead it could start with a harness with memory CRUD tools and then learn how to most effectively use them.
There was a show HN for something similar a couple months ago[0]. Looks like they shut it down. Probably too difficult/low-margin to run as a business, but I think the co-op model you mentioned has potential.
I think a co-op would appeal to the same demographic who are into mesh networks plus all the anti-Flock people. Maybe I'll start something with my friend group and see how it goes from there.
It's interesting because their last model series (Phi) was based around the thesis that high-quality synthetic data is better than a large pre-training corpus.
I think the conduit exception still applies for analog faxes. Which makes no sense, since tapping a fax line is probably way easier than compromising a data center.
Apparently from a third party seller in New York....and tastes really bad. I was surprised steak could be safely mailed in such normal looking packaging!
what a well written article. Very human. Refreshing to read in the era of AI. Witty without trying too hard, genuinely funny, yet informative, and succinct.
Really? Maybe my brain is broken but I saw lots of forced analogies and LLM habits. Like where it does an em dash and a short list:
"I was getting steak ads everywhere—Instagram, news sites, even in places where ads should not be allowed to have that much audacity."
...
"everything simply—salt and pepper, no fancy rubs, no sauce safety net."
...
"with twine—very farmer’s market cosplay, very “trust me, I’m artisanal.”"
Before everyone piles on this comment with "whoosh" and "it was sarcasm" and such — have you noticed that reacting to ironic, sarcastic comments as if they were meant literally is what real LVL 80 trolls do oftener and oftener? On internet, you can never know who is pulling leg...
Interesting to see this after the recent post about Chrome’s on-device model using up 4gb of storage, which frustrated a lot of people [1].
I agree local models are great, and it’s cool that Apple has models built in now. But I feel like it basically has to be an OS level feature or users are going to get upset. I’d certainly rather have a small utility call out to OpenAI than download its own model.
The way I interpret the drama over the Chrome model is that for a large chunk of users, perhaps the majority, Chrome is the OS, and this 4GB model will be their OS Level feature for local AI.
Better auth is great! I love how it's way more hackable than using a something like Clerk. We were able to add a plugin to allow auth via iframe postMessage (embedded in a CRM) and everything worked seamlessly.
I've used it off and on over the last month or so. For more complicated tasks (30+ minutes) it works well, and seems to replace a lot of prompting that I'd normally need to do (e.g. asking questions about requirements, creating specs and implementation plans, staying on task). For simple tasks, it tries to do too much and gets in the way.
I think you’re right that changing its own harness would be bad and skew towards prompt engineering instead of learned behavior. So maybe instead it could start with a harness with memory CRUD tools and then learn how to most effectively use them.
reply