Building tools for #decentralization #dweb #web3. Founder & CTO @ResourcesCo. https://xitter.cf/t.co/f7EcxpMs8U https://xitter.cf/t.co/n5MjFlDgvB
🌐
Joined June 2009
- Tweets6.9K
- Following714
- Followers314
- Likes23.8K
Back to my old username for now. I was paying both for it (by claiming an inactive username) and Grok but I didn't like Grok so I felt I was no longer getting my money's worth.
Benjamin Atkin retweeted
Merging Bun AOT next week, then testing on Claude Code
Expecting 2-3x less memory + CPU & a slightly smaller binary
This is the future of server-side JavaScript
Instead of you rewriting in Rust, we rewrote JavaScript's compiler to emit native code ahead of time
Benjamin Atkin retweeted
Poor security has been cheaper than good security because exploiting it was relatively expensive & time consuming.
But AI has made it cheaper & faster for exploits.
I think this has been a known market inefficiency.
And companies who work to improve security is here to fill that hole by genuinely needing to innovate and improve in the security space
Benjamin Atkin retweeted
litellm pypi package has been compromised: wiz.io/blog/litellm-compromi…
highly recommend running these workloads on a vm locally.
Sandboxing locally is going to become more and more important, do it with smol machines: github.com/smol-machines/smo…
Benjamin Atkin retweeted
If we don't trust agents, why do we trust the software they build?
I suspect that all software in the future will need to be sandboxed.
That's why smol machines is an embeddable VM like sqlite.
Any app can run untrusted code in its own VM, on your own machine.
Isolation shouldn't be pay to play.
Benjamin Atkin retweeted
After a quick bench, if you're using WSL on windows for any thing.
You should be using smolvm instead.
github.com/smol-machines/smo…
Benjamin Atkin retweeted
WE GOT IT! .claw incoming!
.Claw cometh!
The winning applicant for .claw top level domain in ICANN’s 2026 round: the OpenClaw Foundation. Huge step in giving our agents a natural home presence.
Congratulations to @davemorin @steipete and the @openclaw team. Looking forward to great things crawling 🦞 across the web soon.
Benjamin Atkin retweeted
Meet Mistral Large 4, aka Le Chonk.
• 1T parameters, natively multimodal. 49B active.
It is the best open weights model from US or Europe on aggregated benchmarks.
• State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding.
• Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure.
• Available to all via API today. Working with cybersecurity partners privately.
Open weights release end of October.
🤖 Made with AI
Benjamin Atkin retweeted
Smol machines doesn't do snapshots, instead I focus on building a lineage aware file format called .checkpoints.
The idea is that snapshots are a point in time.
But I want to go back to every previous checkpoint kind of like git history, so we can audit or undo an agent's mistakes.
The spec & implementation are 100% open source and public:
crates.io/crates/smolvm-chec…
Benjamin Atkin retweeted
People on windows can use linux very easily and quickly for sandboxing ai or just to use linux.
It's at ~2s right now but will continue to get faster.
Windows users are first class citizens for smol machines: github.com/smol-machines/smo…
Benjamin Atkin retweeted
v1.18 is now out with credential substitution for smol machines.
It's the mechanism to swap in the real key inflight when the placeholder is called within the guest vm.
A compromised agent can't leak what it never had.
Here's an example:
```
smolvm machine run --credential [email protected]
```
github.com/smol-machines/smo…
Porting haproxy from C to Rust overnight. Mind-boggling! 🤯
Benjamin Atkin retweeted
Rogue ai occurrences are accelerating.
And it's looking clear that sandboxing isn't just something that we'll need in the cloud.
We're going to lightweight accessible sandboxing technology for everyone because it's good for both isolating AI from escaping the box + AI from getting inside the box.
It's why smol machines care so much about local vm's being accessible and open source
I was thinking of a #webassembly post I saw that promised not to deviate from the WebAssembly specifications, and that it might increasingly be less optimal because with LLMs it's easier to adapt to new specs. However, ChatGPT helped me find it, and I saw that it was specifically about #wasmtime and it makes sense there – so long as they're OK with people creating forks that do deviate from the spec. bytecodealliance.org/article…
Benjamin Atkin retweeted
Here's how you can branch in smolvm vs firecracker:
smolvm:
`smolvm machine branch --from startedvm --name branchedvm`
github.com/smol-machines/smo…
vs
Firecracker:
pause the vm -> save a snapshot to disk -> launch another vmm -> load snapshot -> resume original : github.com/firecracker-micro…
