brihati
brihati on Hacker News
I use both Codex & Claude Code. With Codex, their long running agents are still not as good as Claude Code. But I don't complain because they burn very less tokens as compared to Claude Code for the same task. But having said that, if I am provided limitless tokens for each of them, my go to harness will be Claude Code
Posted by
brihati on Sunday March 29, 2026 @03:02AM
from the self-post dept.
Here's what I've been watching: startups do the market research, build the product, create the category and Claude Code ships the exact same feature once the market adaptsSo here's what I think the next 6–12 months look like:1. Self-Evolving Agents: Skills exist today as a framework. Agents will begin updating their own skills, rewriting their own playbooks after every task. The system learns...
Posted by
brihati on Friday January 09, 2026 @09:23AM
from the self-post dept.
I was digging through a magic number in code that has lived in the code for quite some time & couldn't figure out why that specific value was chosen. Digged through docs, PRs, PRs' comments, talked/brainstormed with people but no result. After hours of searching, it was buried in commit messageWait... WHAT??? From now on, should I start reading commit messages? Do you have such weird stories?
Posted by
brihati on Saturday January 03, 2026 @02:58AM
from the ask-hn dept.
I am having conversations with engineering leaders where they have expressed concerns that it's not only the code but a lot of other things around code:1. Alignment between engineering teams and other stakeholders which causes the delay in finalising the requirements
2. Scope changing mid sprint, which was not accounted during planning, hence pushing deadlines
3. Engineers who have the most...
Posted by
brihati on Wednesday December 31, 2025 @12:03AM
from the ask-hn dept.
I have been using claude code extensively for coding at my startup, but I am feeling that I can be more productive by utilising the time when the claude code is writing code instead of just staring what claude is doing.One may think that it's a marginal time, but I have timed it, it's 2.5-3 hours per day split over 1/2 minutes window over the whole day.Since the time window is short, I want...
Six thinking hats, taught me how to structure my thoughts by wearing multiple hats where hats are perspective
Interesting take on generational wealth.
Interesting satire, would add it to my reading list
Posted by
brihati on Sunday December 21, 2025 @10:32AM
from the ask-hn dept.
Not looking for books that taught you something new, but ones that changed how you think – the kind that made you see patterns or connections you couldn't unsee. What book rewired your thinking?
Posted by
brihati on Sunday December 21, 2025 @07:57AM
from the ask-hn dept.
We use Claude code internally and it does a good job generating first-pass system designs when given templates and existing architecture. It often captures the obvious components and tradeoffs quickly.Even so, system design still seems slower than expected. People spend days aligning, gathering context, and iterating on designs that feel like they could have started much closer to a workable...
Posted by
brihati on Friday December 19, 2025 @12:11PM
from the ask-hn dept.
Besides HN, are there any communities where I can discuss an idea with peers?
In the software engineering world, in 2026 we saw a wave of code assistant products. In 2026, we will see a wave of designing software architecture products, not just on greenfield projects but also brownfield projects.
Thank you so much for sharing this with the community. Starred the project and will definitely try it out within my company. More power to you!
Interesting, how did you come up with this idea? Have you tried it in production workloads?
I agree. have you tried any framework such as spec-kit by Microsoft to generate feature specs?
Great approach, since you are following a pre-defined set of approaches, have you thought of building an agent for it? or do you have a prompt which helps you with getting the relevant answer?
Posted by
brihati on Saturday December 13, 2025 @03:13PM
from the ask-hn dept.
When starting a greenfield project, do you take the time to write things down sketching out the domain, architectural direction, and key trade-offs to clarify your thinking upfront, or do you prefer to let the design emerge incrementally as you vibe code?
What you say is what you get
In distributed systems, at least we have the variables, functions, pods, log traces, spans etc some pre defined structure, and some level of determinism. I would say Causality is still not fully explored territory when it comes to human brain.
When I think of human brain or may be to some extent LLMs, it's difficult to understand what is invisible. For distributed systems we will build tools, there is ongoing research in LLM Observability, but I wonder what about human brain
Posted by
brihati on Thursday December 11, 2025 @01:50AM
from the ask-hn dept.
Problem with ambiguous boundaries, messy constraints and no linear path to a solution
I come to HN because it's one of the few places left where you can sill watch people think and present new ideas. The people in the world has done intellectual outsourcing, where instead of grappling with the idea themselves, they ask LLMs to predict the next sentence, which has hollowed the real curiosity.
What makes HN valuable to me is the opposite impulse: people trying to understand things for themselves from the community and in the process, maybe, discovering new ideas which LLMs can't supply. Because what LLMs don't know they don't know, LLMs think they know(that's why they predict next sentence) but we know they don't know and still some people think they know
Sometimes, I wish, there is no thinking tax: as a reminder of why this place exists & also to reward people who are still curious and thinkers
I WANT HN TO REMAIN A PLACE WHERE HUMAN CONVERSATIONS STILL HAPPENS.
This was fun, I enjoyed it while claude was busy writing code
BloodHound team: blood is in your hands.
You’ve taken the name of an established security tool and attached it to what, based on your description, looks like a lightly engineered LLM-driven wrapper
First of all, thanks for the contributing to the community. This is a good observability tool to reproduce reasoning paths using structured trace of prompts. During this process, I sometimes do replay the prompts also, especially for some of the use cases where we have observed near deterministic behaviour for some standard prompts. Do you have any plans for adding this feature?
Another question: can your architecture scale to thousands of developers & millions of traces?
Frankly, I was unable to distill what you are trying to achieve here
Posted by
brihati on Wednesday December 10, 2025 @09:37AM
from the brihatijain.com dept.
This article argues that the real fragility in engineering teams isn’t the bus factor, it's the loss of decision context. Most systems depend on knowledge locked in a few heads, and when that disappears, teams pay for it in outages, rewrites, and slow recovery. The post proposes a simple operating model: capturing intent through decision logs, enforcing a technical "constitution" and using automation to reduce drift, so teams can scale without accumulating invisible risk.
I would love to hear from the community how are you handling tribal knowledge within your organisation
Post link: https://brihatijain.com/blog/beyond_the_bus_factor
Really interesting project, it nudges you toward learning instead of mindless feeds.
One suggestion: could you add tags to the research papers so readers can more easily filter by their interests? For example, I’m looking to follow recent work from top venues like NeurIPS specifically on training code-oriented LLMs. Tagging would make it much easier to dive into topics like that.
Thanks for your effort
Really interesting idea, thanks for sharing. When working on new projects, a lot of my learning comes from studying what others have already built so I can reuse patterns around architecture, UX, and product decisions. Those learnings tend to be transferable across tech stacks, so they’re not tightly bound to a specific programming language. Could you share the thinking behind using programming language as the primary way to organize or distill these examples?