Pinned Tweet
Writing bug reports to OSS projects shouldn't be quick.
Maintainers are heroes for donating the amount of time they do to their craft, and you should allocate a modicum of yours to save as much of theirs as possible.
Anything less comes off as obnoxious and entitled, IMO.
henry retweeted
Replying to @ThePrimeagen
AI allowing humans to do less robotic bullshit? Based.
AI allowing humans to have fewer human interactions? Cringe.
Much more value to be extracted from the things you're NOT doing than from the things you are. The latter is finite, but the former is infinite.
So much is possible now.
It's essential to re-evaluate your priors.
The thing people miss with local AI is that it doesn't need to replace your $200/mo frontier inference plans to be viable.
There are tons of little automations that are super viable with small, open-weight models.
The hard part is finding them.
God I am so hyped for overalls.dev
More excited for this than GTAVI
😎 overalls.dev now supports pausing/resuming firecracker machines.
here's how it works:
if the machine is 'pinned' it shows up on the top of your dashboard and is prevented from being deleted for suspended.
if the machine is created via /threads (ie. orb workflow) then the machine is automatically suspended after 4 hours of inacitivity from tool call. a new prompt/toolcall will unpause a machine.
if a network request (ie. vscode web, ssh or shared webapp) arrives it and the machine is paused then it will automatically unpause/resume.
if there is no capacity on the lilly node (the bare metal machine) then it will >automatically relocate the machine< to another lilly node with capacity
machines can now be cloned (ie. forked) with their live memory state instead of being turned off (loss of memory state).
of course you can pause/suspend/clone directly via ssh
all of the above rules hold true even if the machine needs to be relocated to another lilly node with capacity.
tldr; cpu/memory is expensive right now and now resource mgmt is built in as a platform primitive that you can self-host on your own infra 😎
henry retweeted
😎 overalls.dev now supports pausing/resuming firecracker machines.
here's how it works:
if the machine is 'pinned' it shows up on the top of your dashboard and is prevented from being deleted for suspended.
if the machine is created via /threads (ie. orb workflow) then the machine is automatically suspended after 4 hours of inacitivity from tool call. a new prompt/toolcall will unpause a machine.
if a network request (ie. vscode web, ssh or shared webapp) arrives it and the machine is paused then it will automatically unpause/resume.
if there is no capacity on the lilly node (the bare metal machine) then it will >automatically relocate the machine< to another lilly node with capacity
machines can now be cloned (ie. forked) with their live memory state instead of being turned off (loss of memory state).
of course you can pause/suspend/clone directly via ssh
all of the above rules hold true even if the machine needs to be relocated to another lilly node with capacity.
tldr; cpu/memory is expensive right now and now resource mgmt is built in as a platform primitive that you can self-host on your own infra 😎
The thing people miss with local AI is that it doesn't need to replace your $200/mo frontier inference plans to be viable.
There are tons of little automations that are super viable with small, open-weight models.
The hard part is finding them.
I've built an incredible todo system with @liquidai
D1-3B for action routing (e.g. create new or edit existing)
LFM-2.5-24B-A2B for synthesizing transcription blobs into titles, descriptions, and deadlines
LFM-2.5-Embedding-350M for semantic lookups
Local AI at its best.
henry retweeted
Following Ukrainian strikes on Russian data centers:
Tucker Carlson's views dropped 71%
Douglas Macgregor's views dropped 62%
TCN views dropped 34%
...or even otp-js 😱
OK being able to stick an entire runtime and agent development environment in a V8 isolate is dope.
@elixirlang folks if TypeScript (or any language) is to "win" in the AI era, it'll be because of stuff like this.
Legit think we might need an otp-rs...
youtu.be/ND_kRgU_WlY
OK being able to stick an entire runtime and agent development environment in a V8 isolate is dope.
@elixirlang folks if TypeScript (or any language) is to "win" in the AI era, it'll be because of stuff like this.
Legit think we might need an otp-rs...
youtu.be/ND_kRgU_WlY
Announcing tsc-rs (aka ts-rust), my complete rewrite of the Typescript compiler, type checker, and LSP, all in Rust.
This is a project I've had agents working on for 5 months now. I burned ~$400k of Codex tokens and got nowhere. Burned ~$20k of Opus and got there in 2 weeks.
I have not read a single line of the code.
tsc-rs is an open source drop-in replacement for tsc, and it's available now.
We’re releasing a broad range of new mathematical results produced by an internal frontier model.
We’ve been consulting with the independent Advisory Group on Mathematics and Artificial Intelligence at the Institute for Advanced Study, and we have drawn on their advice and public recommendations to inform how we release these results.
github.com/openai/math
🤪
Replying to @maria_rcks
Alpha increasingly comes from one's ability to break out of boring gradient descent and find novel local minima.
Wacky ideas are the new moat.
Sheffield sold a QL1.2 today because of Instinct.
Had a conversation a couple weeks ago about wanting a QL1 but they were sold out. Went from not knowing the QL1.2 existed to having one ordered for me in like four WhatsApp msgs.
This is gonna be huge.
Replying to @GeoffreyHuntley @_cartermp
Instinct is the only one with a real shot IMO because they're leaning HARD into making it feel like texting a person, and also focusing on consumerism for their monetization strategy.
Methinks the "ooh I want that" -> "here's a link" flow is gonna hit for a lot of people.
henry retweeted
Calvin was a true prophet of our time
We’re releasing a broad range of new mathematical results produced by an internal frontier model.
We’ve been consulting with the independent Advisory Group on Mathematics and Artificial Intelligence at the Institute for Advanced Study, and we have drawn on their advice and public recommendations to inform how we release these results.
github.com/openai/math


















