poshmosh
Joined 4 years ago
Karma
24
Submissions
20
Member since
Mar 22
Recent submissions
Comment · 26 days ago
You can pass a youtube video of a tutorial directly to LLM, LLM can then use MCP to do what the tutorial says.
Comment · 26 days ago
If you have an LLM and MCP why do you need a tutorial? Why would I watch a tutorial when the LLM can tell me how to use a feature? There is not a moat just because there are tutorials. That moat is gone. I don't need to watch tutorials anymore.
Comment · 26 days ago
Every piece of beta software that has ever existed, has bugs. AI doesn't change this. Software development has largely changed to build with AI first, get basic things working, iterate and fix. This is just the reality older developers just have to accept.
Comment · 26 days ago
Most people are going to use AI to interact with this. I think the notion that Adobe will always be the leader because of content and tutorials is wrong. Why would I watch a tutorial if I could just use MCP and ask LLM how to do something?
Comment · 3 months ago
I’m the creator of Pulsys.
I originally built this to help with self-hosting Hugging Face models, but it evolved into an authenticated pull-through cache.
A big part of this project was an experiment to see how far I could get Cursor + (Opus/Fable) to optimize the hot path. I initially used fasthttp and Go's net/http, but after some deep optimizations, the only way to squeeze out more performance was to eliminate syscalls.
I ended up building two optimization paths that use a custom-built HTTP/1.1 parser: one for macOS using sendfile + sf_hdtr, and one for Linux using io_uring. For anyone interested in the threat model or how the custom parser is tested against Go's standard library, I wrote a detailed security breakdown here: https://pulsys.io/docs/security/
The result is that it can sustain 1.36M req/s at 4 KiB and 90 GB/s at 16 MiB on an EC2 instance (see benchmarks https://pulsys.io/docs/benchmarks/)
It drops right in front of existing clients (just set HF_ENDPOINT).
I’d love to hear your thoughts, feedback, or any questions on the AI-assisted optimization process!
Comment · 1 year ago
I have 14 YOE and its the opposite. Really brilliant jrs don't have the experience to know the consequences of their designs, they build fast under pressure. They reinvent things that already exist (they don't know because they a Junior).
Seniors have PTSD and push back.
Comment · 1 year ago
I worked in the music streaming industry, which involves ingesting 10's of millions of XML files. Absolutely do not use XSLT. Schema changes between different versions of DDEX were a nightmare for all the legacy XSLT we had.
Comment · 1 year ago
Comment · 1 year ago
Comment · 2 years ago
I don't see any reason to use this for AWS over CDK. CDK already has some pretty higher level modules that make it really easy to setup ecs, k8s, vpc, ect.