> There's just not a lot of juice left to squeeze for Gemini to tell you exactly how tall Ke$ha is or when the last time Brittney Spears went to jail was...
But there is a ton of juice left to squeeze when it comes to post-training/RL for a ton of useful things in practice, right?
It’s been amazing seeing how good modern model tool use is for example, and I bet there is a lot of room for improvement still (no doubt that a ton of improvement can be made more easily on the agent harness front or via post-training regimes like LoRa (which does support to your point about diminishing pre-training juice))
Can you provide some info on how to use the max plan / ChatGPT pro subscription via OAuth? I was about to subscribe but wasn't entirely sure how to configure that
Woah - I just drove by the JCV institute in La Jolla yesterday and felt thinking that the organization was really monumental to synthetic biology. Rest in peace
The company I work at has been building a dementia prevention program covered by most insurance plans in the US.
Our clinicians work directly on helping understand risk of neurodegenerative disease and help tailor personalized plans to improve outcomes.
A recent lancet study concluded that around 45% of dementia cases are preventable [0]
Happy to answer any questions people have.
Different person, unrelated to the above advertisement but:
Sometimes any diet.
Mental health struggles can exacerbate, (and be exacerbated by!) forgetting to eat, not wanting to eat,
forgetting or passing up the things that keep you in homeostasis, choosing the less correct things because of an emotional response, a physiological response in a “diminished” state.
I asked because I already know the correct answer, which is "metabolic psychiatry", meaning versions of keto/carnivore/epilepsy-keto diets (the latter is the strongest).
This is really interesting, congrats on the launch.
The use case I’m trying to solve for is building a coding agent platform that reliably sets up our development stack well. Few questions!
In my case, I’m trying to build a one-shot coding agent platform that nicely spins up a docker-in-docker Supabase environment, runs a NextJS app, and durably listens to CI and iterates.
1) Can I use this with my ChatGPT pro or Claude max subscription?
2)
We don't support docker-in-docker yet, but that's something on our short term roadmap. We have the need for this ourselves! For now, you could call a different service to spin up your sandbox with the image of your codebase. Not ideal, but this is what we do now.
Yes, you can use your own subscriptions as long as you follow their guidelines
Dagger (dagger.io) has its own container execution stack, and supports dagger-in-dagger natively, with logical scoping, and without depth limit. Would love to show you both a demo, if you're interested!
(Disclaimer, I'm the CEO of Dagger)
I founded Docker, and lack of proper nesting support was always a pet pieve of mine. I couldn't fix it in Docker, so I fixed it in Dagger instead :)
This demo started out as really cool - but the very first generated was terrible (in that it actually would have been very negative for our brand)
Happy to discuss what exactly was problematic with you guys - so please take my comment constructively.
This is really interesting! Pretty remarkable that the key insight isn't just about crossing the BBB—it's about repairing the transport machinery itself.
We're building BetterBrain around this insight—catching vascular and metabolic risk factors that compromise BBB integrity years before severe pathology. Not replacing breakthrough therapies like this, but complementing them by intervening earlier in the cascade.
(www.betterbrain.com/insurance if anyone would like to try - its $0 with most insurance plans)
It’s been fairly handy - I recently spun this up using glm5.2