The uncomfortable part of becoming a builder
Nobody really talks about how uncomfortable is it to start building and its not the coding part it is "what if nobody really cares ?" part.
Like you have an idea you genuinely like but then suddenly your mind starts overthinking and gives you 50 reasons why it won't work.
Should VCs take on the (financing) role instead of the state/government?
Yesterday, @rrhoover shared a Forum about Y Combinator and the topics they are interested in.
These 5 grabbed my attention in the list:
AI for Scientific Advancement
Healthcare AI
The Future of Education
AI Residential Security
AI Research Labs
Most social tools feel like they were built for someone else.
My friend and I were running into the same brick wall over and over again: we'd attempt a tool, be excited for about 10 minutes and then it'd be like it was built for another team, another workflow, or honestly, another era.
Some were clunky. Some were too complicated. None of them worked how we needed.
So we set out to build Loopify, something we'd actually want to use ourselves:
Quick. Efficient. Simple. Doesn't get you thinking you require a training program just to book a TikTok.
We are looking for as much user feedback as possible. Talking with teams, individual creators, small brands, anyone who's had to fight through tools just to keep up online.
If that sounds like you, I'd love to hear:
What's your biggest friction point with current tools?
What's one teeny feature you'd love to have but never see?
Or just something you dislike doing that could be simpler?
Seriously appreciate any ideas you pitch our way.
Are AI memory systems actually needed?
Memory systems for products like Claude Code and Codex might not be as reliable as they seem because they're heavily dependent on the harness, how the LLM is guided to retrieve and use them.
More customizable agents like OpenClaw and Hermes solve some of this with plugins and custom memory systems.
But then you need memory that works across devices, local sessions and cloud agents.
So I'm wondering : is AI memory actually a product, or just infrastructure agents will eventually handle themselves?
For marketplace founders: how small did you go before expanding?
I m building a two-sided local services marketplace, and one of the questions I keep coming back to is how small the initial market should be.
At first, Houston felt like the obvious starting point. But the more we build, the more I think city-level thinking may be too broad for an early marketplace.
Not enough News Apps!
I have long struggled with trying to consume news on my phone. I think news is still too high volume, uncontextualised and not built for learning. Do you guys have any good examples or ideas of News Aggregration app that can be built for people who are not news enthusiasts but would like to know whats happening in the world?
Which CSS approach should we default to for new web projects? Discussion
Hi!
I wanted to gather some opinions from different people as to which styling approach we should use primarily while developing web applications for long-term maintainability.
For me, it is Vanilla CSS (or SCSS) because it forces you to understand core CSS principles and keep your HTML clean. If your team understands standard CSS architecture, they can easily maintain the codebase without learning a framework's specific syntax.
Cloudflare's new "Gatekeepers" concept for agent approvals — anyone tried it?
Cloudflare put out an open-source project called Cloudflare OS a week or so ago, and the part that caught my attention is "Gatekeepers": a capability-based layer that requires async approval before an agent can take a sensitive action. It got a lot of attention on HN specifically for that idea, more than the platform itself.
I've been dealing with a version of this same problem: figuring out where the line is between actions an agent should just do versus actions that need a human to say yes first. The "async" part is what's interesting to me. Most approval flows I've seen block the whole turn until someone responds. Doing it asynchronously means the agent can keep working on other things while one action sits waiting.
Curious if anyone's actually wired this into a real workflow yet, and whether async approval ends up feeling smoother in practice or just adds a different kind of complexity (tracking what's pending, handling timeouts, etc).
When building production AI Agents, do we over‑invest in base model upgrades?
Every time a new agent focused LLM comes out, there is a lot of excitement around improved reasoning and tool calling performance. Many builders immediately plan to migrate their agent workflows to the newest model hoping for instant quality gains.
From my experience building agent powered tooling, model upgrades only solve a small portion of real world pain points. Even strong models behave poorly without solid surrounding engineering.
Things like structured output repair, dynamic context management, failure fallback logic, and tool call loop protection often make a bigger difference to end user reliability. You can swap in a state of the art model, yet still get broken results if your orchestration layer is weak.
Benchmarks and demo performances rarely reflect messy real user inputs, interrupted sessions and long running conversations.
Has AI made it too easy to keep building instead of validating?
disclaimer: I m guilty of this.
The more agentic capability i seem to have at my disposal, the deeper i go. But is that where I should be?