Viewing profile — fazlerocks

For me: 1. ChatGPT desktop. This is the one I probably use the most without even thinking about it. 2. Gemini. I used 2.5 a lot for content stuff and recently started trying Gemini…

Feels like we’re all shipping faster, but the old “just write more tests” advice isn’t keeping up. Teams are smaller, release cycles are tighter, and AI is sneaking into a lot of w…

Hi HN, I built Mail42 ( https://mail42.ai ) to make it easier to test email flows without dealing with regex or messy parsing. The pain point: whenever I tested signup or checkout …

honestly? teaching or coaching. been thinking about this a lot lately and realized the skills that made me good at building products, breaking down complex problems, explaining thi…

we've shifted to focusing way more on problem-solving ability during interviews rather than just coding skills still do technical screens but now we give people access to AI tools …

we've tried a bunch of different approaches and honestly the best feedback comes from getting people in a room (or zoom) together widgets are fine for quick "this button doesn't wo…

the best "payment" is often just updating them on how their help changed your trajectory. a simple message years later saying "that advice you gave me led to X" means everything al…

This is actually a really cool direction, using LLMs to interact directly with Android UIs could solve the brittleness problem that's been killing traditional automation. Like just…

We're building tools that could genuinely make people's lives better, but instead most companies are laser-focused on "how many jobs can we eliminate?" The whole conversation aroun…

Been messing around with the different memory files and honestly it's pretty useful once you get the hang of it. I mostly use: Project ./claude.md - team stuff like our weird API n…

We're running LLMs in production for content generation, customer support, and code review assistance. Been trying to build a proper evaluation pipeline for months but every tool w…

Learn prompt engineering and how to effectively use AI coding assistants… that's immediately useful and will save you hours daily. Vector databases (Pinecone, Weaviate) and buildin…

Honestly X is still pretty good for this if you follow the right people. The AI/ML research community is super active there - Andrej Karpathy, François Chollet, Yann LeCun, etc. Pl…

[flagged]

Right. We're optimizing for the wrong metrics. Hours spent arguing if something is a 3 or 5 story points could've been spent just building it. The obsession with predictability in …

Running Llama 3.1 70B on 2x4090s with vLLM. Memory is a pain but works decent for most stuff. Tbh for coding I just use the smaller ones like CodeQwen 7B. way faster and good enoug…

Looking to build something open source and trying to figure out what tools everyone pretends to love but actually hate. I'll start. Jira. We all use it, we all hate it, nobody admi…

4 cents per request adds up real quick when it's doing stuff you didn't even ask for. Have you tried disabling the GitHub integration entirely? Wondering if that's what's triggerin…

This is pretty cool - the Jira/Linear integration could save a ton of manual work. How do you handle test data setup and teardown? That's usually where these workflows get messy. F…

The indexing costs would be nuts - Anna's Archive is like 200TB+ and growing fast. Even with decent search infra you're looking at serious compute/storage costs. Plus there's the o…

Have you considered implementing velocity limits and requiring phone verification for new accounts? We faced similar issues and found that slowing down rapid fire purchases + requi…

Thanks for the detailed response! I actually tried fly.io briefly with Next.js apps and the deployment experience was smooth. Really interesting to hear you're using it for AI work…