As someone who used priming heavily at Google, and its wide use in social networks to billions in revenue. I’m gonna go with the academics trying to take this down are BS.
Adam Curtis even suggests lightly that the takedown of priming in academia was paid for to bury its actual effectiveness (and liability by implication)
priming obviously works. it is inherent in the physical structure of the brain. nerve endings from various all over the body terminate in different physical locations in the brain, and then these are interlinked in an adaptive biological mesh network. nerve responses are triggered by cascades of correlated impulses across different nerve endings, so at a physical level a strongly correlated signal from any two major nerve groups will trigger a sympathetic response when one of them fires independently. the experiments that social scientists come up with may be flawed, but this is definitely how my brain works, so i don't need a study to prove it.
For some definitions of better, yes. Chinese is more token efficient for representing fixed text, for example, although this does not always lead to better performance on downstream tasks.
True. I suspect it's still hard to tell whether the bottleneck is the language itself, the tokenizer, or just the overwhelming amount of English training data.
As the author - this was adapted from a thread posted on X in March (linked in article). AI did the adaptation, I wrote the original article. It seems like it inserted grammatically correct hyphens, otherwise the copy is mine.
Hello, I am the author - this is not an LLM-generated article, I wrote this by hand and had an LLM adapt it from a thread on X. You can see the original thread here: https://x.com/mathemagic1an/status/2035850046735098065
> the fact that language models have human-interpretable representations and neurons has been known since BERT... Circuits research also does not come from Anthropic...
The article does not claim Anthropic invented the field, rather that they have had important contributions to it. This is intended as an overview into a specific set of ideas that are working for mechanistic interpretability. Not a formal literature review.
Would love to understand how you compare to other providers like Modal, Daytona, Blaxel, E2B and Vercel. I think most other agent builders will have the same question. Can you provide a feature/performance comparison matrix to make this easier?
I'm working on an article deep diving into the differences between all of us. I think the goal of Freestyle is to be the most powerful and most EC2 like of the bunch.
I haven't played around with Blaxel personally yet.
E2B/Vercel are both great hardware virtualized "sandboxes"
Freestyle VMS are built based on the feedback our users gave us that things they expected to be able to do on existing sandboxes didn't work. A good example here is Freestyle is the only provider of the above (haven't tested blaxel) that gives users access to the boot disk, or the ability to reboot a VM.
Fly.io sprites is the most similar to us of the bunch. They do hardware virtualization as well, have comparable start times and are full Linux. What we call snapshots they call checkpoints.
The big pros of Sprites over us is their advanced networking stack and the Fly.io ecosystem. The big cons are that Sprites are incredibly bare bones — they don't have any templating utilities. I've also heard that Sprites sometimes become unavailable for extended periods of time.
The big pros of Freestyle over Sprites is fork, advanced templating, and IMO a better debugging experience because of our structure.
Thanks for the thoughtful response. I'm predominantly a self-hoster, but I think your product makes a lot of sense for a wide variety of users and businesses. I'm excited to try out freestyle!
Freestyle/other providers will likely provide better debugging experience but thats something you can probably get past for a lot of workloads.
The time when you/anyone should think about Freestyle/anyone is when the load spikes/the need to create hundreds of VMs in short spikes shows up, or when you're looking for some of the more complex feature sets any given provider has built out (forks, GPUs, network boundaries, etc).
I also highly recommend self hosting anything you do outside of your normal VPC. Sandboxes are the biggest possible attack surface and it is a feature of us that we're not in your cloud; If we mess up security your app is still fine.
Obviously your service/approach is different than exe, more like sprites but like you said more targeted/opinionated to AI coding/sandboxing tasks it looks like. Interesting space for sure!
I built yoloAI, which is a single go binary that runs anywhere on mac or linux, sandboxing your agents in disposable containers or VMs, nested or not.
Your agent never has access to your secrets or even your workdir (only a copy, and only what you specify), and you pull the changes back with a diff/apply workflow, reviewing any changes before they land. You also control network access.
Still WIP, but the core works — three rootfs tiers (minimal Ubuntu, headless Chromium with CDP, Docker-in-VM), OCI image support (pull any Docker image), automatic thermal management (idle VMs pause then snapshot to disk, wake transparently on next API call), per-user bridge networking with L2 isolation, named checkpoints, persistent volumes, and preview URLs with auto-wake.
Fair warning: the website is too technical and the docs are mostly AI-generated, both being actively reworked. But I've been running it daily on a Hetzner server for my AI agents' browser automation, and deploy previews.
I'd love any feedback if you want to go ahead and try it yourself
We do auto suspend depending on your configured timeout. We'll pause your VM and when you come back the processes will be in the exact same state as when you left.
But your pricing page suggests that that is not available without a subscription: in the on-demand pricing section "persistent Snapshots" and "Persistent VM's" have an 'x'.
We do not allow long term persistence for the free tier.
This is purely a defense mechanism, I don't want to guarantee storing the data of an entire VM forever for non paying users. We have persistence options for them like Sticky persistence but it doesn't come with the reliability of long term persistence storage.
