I don't know about Jetstream, but redis cluster would only ack writes after replicating to a majority of nodes. I think there is some config on standalone redis too where you can ack after fsync (which apparently still doesn't guarantee anything because of buffering in the OS).
In any case, understanding what the ack implies is important, and I'd be frustrated if jetstream docs were not clear on that.
To the best of my knowledge, Redis has never blocked for replication, although you can configure healthy replication state as a prerequisite to accept writes.
This makes sense to me. Where I work our ai team set up a couple h100 cards and are hosting a newer model that uses up around 80GB vram. You can see the gpu utilization on graphana go to like 80% for seconds as it processes a single request. That was very surprising to me. This is $30k worth of hardware that can support only a couple users and maybe only 1 if you have an agent going. Now, maybe we're doing something wrong, but it's hard to imagine anyone is going to make money on hosting billions of dollars of these cards when you're making $20 a month per card. I guess it depends on how active your users are. Hard to imagine anthropic is right side up here.
So in terms of OCR, does the neural network 'map' the words into an embedding directly, or is it getting a bunch of words like "Hamlet's monologue" and mapping that to an embedding? Basically what I'm asking is if the neural network image encoder is essentially doing OCR 'internally' when it is coming up with the embedding (if that makes any sense).
13 minutes in Andrej is talking about how the models don't even really need the knowledge, it would be better to have just a core that has the algorithms it's learned, a "cognitive core." That sounds awesome, and would shrink the size of the models for sure. You don't need the entire knowledge of the internet compressed down and stashed in vram somewhere. Lots of implications.
Well I don't know about others here, but I think its cool. If you can make the setup super readable and get the performance of C then why not? Especially now when you can get claude to write a bunch of the framework for you. Add in whatever you need whenever you need it and you automatically have a platform independent web framework that's no bigger than what you need and likely decently performant.
Haha, I have used AI in some parts of it - mainly the JSON part because I could not wrap my head around it for the life of me. But I am proud that 90% is self written!
In that case the json parse function might be a bit of a challenge. It should actually be pretty straight forward with the builder functionality you’ve got in there. Loop over the input and use a state machine (switch block with a state variable) keep track of what you’re doing. Oh and you’ll need to recurse or otherwise use a stack to keep the nesting levels correct. Ie objects that contain arrays or objects, arrays that contain arrays, etc.
I think the old HN ethos that I loved, on full display here, won't survive intact in the AI era. It'll have to change from "It is cool to try making <neat tool> in <non obvious language>". Such a project is now a prompt away, and there's light-years of distance between a carefully hand crafted version and something that is posted aspirationally by an AI.
Every agent I know of or use will always say they built "Production ready, secure, fast package for X" if you ask them to build that, but they rarely actually will. It takes enormous time and effort to actually do that, and any first iteration of "production ready" is definitely aspirational until it actually hits the real world and survives. I'm speaking from experience, fwiw.
I think its just a simple matter of aesthetics. Some people find violence ugly, and don't like looking at it. Some people think that by looking at it you're somehow coming to a greater understanding of the world or something. Maybe that is the case for some super sheltered individuals, but I doubt it's the case on the whole.
If anyone has any ideas on what the point of violence in art is, I'm open to hearing it. Obviously horror is a genre and so is gore, and people seem to enjoy being shocked. I don't think that is what McCarthy was going for though. And he wasn't going for the vengeance-catharsis angle like Tarantino either.
Agreed agentic coding is a huge change. Smart startups will be flying but aren't representative. Big companies won't change because the staff will just spend more time shopping online instead of doing more than what is asked of them. Maybe increased retail spend is a better measure of AI efficacy.
I know, I don't understand what problems people are having with getting usable code. Maybe the models don't work well with certain languages? Works great with C++. I've gotten thousands of lines of clean compiling on the first try and obviously correct code from ChatGPT, Gemini, and Claude.
I've been assuming the people who are having issues are junior devs, who don't know the vocabulary well enough yet to steer these things in the right direction. I wouldn't say I'm a prompt wizard, but I do understand context and the surface area of the things I'm asking the llm to do.
From my experience the further you get from the sort of stuff that easily accessible on Stack Overflow the worse it gets. I've had few problems having an AI write out some minor python scripts, but yield severely poorer results with Unreal C++ code and badly hallucinate nonsense if asked in general anything about Unreal architecture and API.
Does the Unreal API change a bit over versions? I've noticed when asking to do a simple telnet server in Rust it was hallucinating like crazy but when I went to the documentation it was clear the api was changing a lot from version to version. I don't think they do well with API churn. That's my hypothesis anyway.
I think the big thing with Unreal is the vast majority of games are closed source. It's already only used for games, as opposed to asking questions about general-purpose programming, but there is also less training data.
You see this dynamic even with swift which has a corpus of OSS source code out there, but not nearly as much as js or python and so has always been behind those languages.
Clarifying can help but ultimately it was trained on older versions. When you are working with a changing api, it's really important that the llm can see examples of the new api and new api docs. Adding context7 as a tool is hugely helpful here. Include in your rules or prompt to consult context7 for docs. https://github.com/upstash/context7
reply