Viewing profile — wehadit
wehadit
HN member- Joined
- Fri, Feb 07, 2025, 12:21 AM UTC
- HN karma
- 1
- Public activity
- 22 items
- HN profile
- View on Hacker News ↗
About wehadit
No profile information was provided.
Recent public activity
- story
-
comment
Comment #47359915
Why not get it 1st time right before it's sent to the Sr. Devs? Granted AI creates sloppy code, but there are ways to make it Sr. Dev grade, mainly by getting rid of what I call Bu…
-
comment
Comment #47356722
If you use the models like we execute coding tasks, older models outperform latest models. There's this prep tax that happens even before we start coding, i.e., extract requirement…
- story
- story
- story
- story
- story
- story
- story
- story
- story
- story
- story
- story
- story
-
comment
Comment #46140892
Thank you will have a look
-
story
Stop Blaming Embeddings, Most RAG Failures Come from Bad Chunking
Everyone keeps arguing about embeddings, vector DBs, and model choice, but in real systems, those aren’t the things breaking retrieval. Chunking drift is. And almost nobody monitor…
-
comment
Comment #46130580
That's another way to look at it. Getting AI to reliable and accurate output is where we feel there are steps that'll need better structure, like for Ingesting and chunking strateg…
-
story
Most Agentic AI failures I've debugged turned out to be ingestion drift
Over the last few months, we’ve been working on creating an autonomous Agentic AI, and something unexpected kept showing up. I went in thinking the issues were with embeddings or t…
-
story
Is generation of reliable tailored code helpful?
Hey devs, I am building an agentic AI to be the AI tool for developers. I was wondering if it'll be helpful if the agentic AI generates the 1st working ver of app in one prompt wit…
-
story
We need more than AI auto complete to do what matters most
The reality is that since the 90s, we've all gone from spending 70% of our time on things we enjoy to 30%. This shift is due to info overload, multitude of apps and processes creat…