HN user
I had a strange call with a support rep recently.
They sounded a tinge strange, like they’ve almost crossed the uncanny valley, only to succumb at the final 3% stretch.
I was suspicious, but their ability to understand my complex request and the relatively low latency make an LLM -> TTS or e2e voice model unlikely.
This post finally solved the mystery.
Motor: https://www.aliexpress.us/item/3256804897857573.html?gateway...
The 90KV version is what you want.
For legged, you want high torque and backdriveability (for shock absorption).
Agricultural drone motors like the eaglepower 8308 are ideal.
They’re cost effective, (~$80 from aliexpress) & you can pair them with a 3d printed cycloidal drive to fulfill both requirements.
Industry actuators are an order of magnitude more expensive than this.
Extra: If you go down this path, you’ll need a driver. The Xdrive is frequently recommended, but there’s a clone that’s significantly cheaper: https://makerbase3d.com/product/makerbase-xdrive-mini-high-p...
A seldom appreciated benefit of gruvbox: like vim binds, it's available everywhere. If it has a theming system, somebody ported gruvbox to it.
Why would you want to ssh into a machine that's not yours? That's a violation of the Computer Frauds and Abuse Act, up to 10 years in prison!
Tragedy of the aggregate.
There are existing solutions for queues in Postgres, notably pgmq.
Despite sentiments around Mojo being negative on HN due to the stack not being OSS, this is the ultimate goal of Modular.
https://signalsandthreads.com/why-ml-needs-a-new-programming...
The blog's title can be misleading here, "we" in this context refers to the Cognition team. I don't work at Cognition, just thought this was interesting.
On August 29, a routine load balancing change unintentionally increased the number of short-context requests routed to the 1M context servers. At the worst impacted hour on August 31, 16% of Sonnet 4 requests were affected.
Interesting, this implies that the 1M context servers performs worst at low context. Perhaps this is due to some KV cache compression, eviction or sparse attention scheme being applied on these 1M context servers?
That’s true if we’re evaluating Zed as a product, but the GP is discussing Zed U.I perf specifically.
Snappiness is the primary reason for using Zed.
The other examples you listed are valid, but A.I tab auto complete is a model & inference issue unrelated to the editor.
I have the same set of requirements you’re describing and Obsidian is perfect.
You can disable the graph feature and never link any notes.
This is both the largest oss model release thus far, and the largest Muon training run.
leerob is so active in the space that I didn't realize until reading this that he isn't Vercel's founder.
I’m confused on what this is based on the landing page.
Version control isn’t specific to A.I workflows, what does this add on top of git?
Is this a worktree type solution so you could make parallel edits?
It's either sticky sessions or an lb that keeps track of prior sequences and route to the instance with the largest match. https://docs.sglang.ai/router/router.html
There is windows sandbox: https://learn.microsoft.com/en-us/windows/security/applicati...
Not available on the home edition of windows though.
you use a neural audio codec to encode audio into codebooks
then you could treat the codebook entries as tokens and treat audio generation as a next token prediction task
you then take the codebook entries generated and run it through the codec’s decoder and yield audio
it works surprisingly well
speech text models (tts model with an llm as backbone) is the current meta
This is delightful.
They’re using the FS for caching the KV caches of past requests. It’s why they’re able to charge so little on prompt cache hit.
thank you steve, i’ve been excited for this!
30 messages per week
That’s an on-demand server, not serverless.
Elixir. The community is nice and welcoming.
Everyone is passionate about the project, you can feel the care that’s being poured into the ecosystem.
I thought it was a new Gruv Box theme. However, this is equally as cool.
It looks fine to me.
Fortunately, it's billed as average DAUs. So a user logging in once a day over 30 days would count as 1 DAU.
The frontpage should make it clear which open source project corresponds to which Ory Network product.
I was confused about that for a while.
Ex:
Login & Authentication -> Kratos
Permissions & Access Control -> Keto.
You could take some cues from Grafana here.
Similarly to Ory, their product is backed by OSS.
Their frontpage’s navigation bar makes it clear which is backed by which.