oh, honey.
24,625 karma · joined December 9, 2015
ai engineer pod/news: https://latent.space/
conference: https://ai.engineer
devrel/devtools: https://dx.tips/
personal blog: https://swyx.io/ideas
book: https://learninpublic.org/
but you can also email username [at] ai dot engineer
---
meet.hn/city/37.7792588,-122.4193286/San-Francisco
Socials:
- x.com/swyx - youtube.com/@swyxtv
oh, honey.
i think the real ones know this is the tip of the iceberg? hparam tuning, data recipes, data collection, custom kernels, rl/eval infra, all immensely deep topics that would condense multiple decades of phd lifetimes to produce SOTA performance (in both senses of the word) like this.
i would also calibrate what you are impressed by. simply waiting is a posttrain thing - the fact that gemini and oai have not prioritized it is not something you should overindex on as hard. what they showed with full duplex is technically far far harder to achieve
maybe to put it in a way where your values are aligned, i'm a curious person, and i learn a lot from the discussions that happen right on HN rather that only going to the source.. indiscriminate comment count damping takes away/lowers visibility of the most interesting comments that would provoke my curiosity.
one could instead do any sort of basic classifier system ranging from bag of words to running a ModernBERT to rate flamewarness and differentially apply the downrank based on "flamewar score" rather than "really poor proxy to flamewar score"
just beautiful. nothing to add, clap clap
also share your scripts pls?
hmm so airbyte agents could serve as a form of MCP gateway, or a key building block of an MCP gateway, which btw is how anthropic uses mcp themselves for all their internal apps https://www.youtube.com/watch?v=CD6R4Wf3jnY&t=1s&pp=0gcJCd4K...
i think my most sad/interesting observation about ai engineers is that many ai apps are super data hungry, but many dont have the necessary data engineering background to even know they need an airbyte or what tradeoffs to make in an etl pipeline. would love a "data engineering for ai engineers" type braindump session from someone from airbyte at AIE (https://ai.engineer/cfp )
lets get nitty gritty on this - can you say how you did this? because a lot of people think this is an unsolved problem
(would teach me a little about Zig, about which i know 0)
maybe cache this thing my guy you're just doing a bunch of reads
---
constructive suggestions
- you have a pretty cheap process here, and HN exposes historical posts by date. perhaps worth running this back the last 2 years to reconstruct a history of sentiment?
- introduce alternative sorts around the net positive/negative sentiments and absolute positive sentiments, similar to State of JS (https://stateofjs.com) - you'll see the gpt outperformance more
- matching of Opus 4.7 and Opus Latest seems sus?
that doesnt sound too terrible to be honest. TIL that 8am-2pm is 2x usage.
(lmk if you'd like an ai.engineer stage to do it on)