Hacker News: brihati

New comment by brihati in "Show HN: State of the Art of Coding Models, According to Hacker News Commenters"

brihati — Mon, 04 May 2026 09:45:51 +0000

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

Next 12 months: Production Code that runs itself

brihati — Sun, 29 Mar 2026 07:02:21 +0000

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 adapts

So 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 to improve itself. Lots of startups already working to solve this problem

2. Local → Remote → Global Sessions: They shipped local where an engineer works on few repositories within Claude Code. Then recently remote to push local sessions to remote. The trajectory seems obvious. Soon, the entire organisational codebase becomes a few global sessions tended by few architects within the organisation

3. Moving into the Production Layer Claude Code moves from the editor into the infrastructure itself watching, identifying bugs, shipping fixes.

4. [2026] The Great Reallocation This is the hardest one to say. Companies won't just hire fewer engineers. They'll restructure around the assumption that the system runs itself with fewer engineers.

I would love to be proved wrong!!

Comments URL: https://news.ycombinator.com/item?id=47560987

Points: 4

# Comments: 0

Ash HN: Excavating Decision Archaeology

brihati — Fri, 09 Jan 2026 14:23:59 +0000

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 message

Wait... WHAT??? From now on, should I start reading commit messages? Do you have such weird stories?

Comments URL: https://news.ycombinator.com/item?id=46554140

Points: 2

# Comments: 0

Ask HN: The Alignment Tax

brihati — Sat, 03 Jan 2026 07:58:38 +0000

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 context of system X, is on leave or have left the company, hence decisions are delayed 4. Senior engineer changing the approved design mid sprint because of some flaws in approved design 5. Identified dependencies on other teams who have their hands tied up with other urgent tasks .... & so on

Curious what this looks like at your company. What's the most expensive coordination failure your team has experienced? How much did it cost the company?

Comments URL: https://news.ycombinator.com/item?id=46473820

Points: 1

# Comments: 0

Ask HN: What to do when Claude Code is writing code?

brihati — Wed, 31 Dec 2025 05:03:48 +0000

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 something that I can complete in that time window. I have been solving chess puzzles during that time, but want to do something which benefits my startup in the long run, maybe learn something new.

How are you utilising that time?

Comments URL: https://news.ycombinator.com/item?id=46441467

Points: 2

# Comments: 2

New comment by brihati in "Ask HN: What's a book that fundamentally altered your mental models"

brihati — Mon, 22 Dec 2025 00:08:12 +0000

Six thinking hats, taught me how to structure my thoughts by wearing multiple hats where hats are perspective

New comment by brihati in "Ask HN: What's a book that fundamentally altered your mental models"

brihati — Sun, 21 Dec 2025 18:29:13 +0000

Interesting take on generational wealth.

New comment by brihati in "Ask HN: What's a book that fundamentally altered your mental models"

brihati — Sun, 21 Dec 2025 16:09:31 +0000

Interesting satire, would add it to my reading list

Ask HN: What's a book that fundamentally altered your mental models

brihati — Sun, 21 Dec 2025 15:32:37 +0000

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?

Comments URL: https://news.ycombinator.com/item?id=46345549

Points: 44

# Comments: 52

Ask HN: What is still hard about system design with AI?

brihati — Sun, 21 Dec 2025 12:57:10 +0000

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 draft.

For those who already use AI tools while designing systems:

What parts of system design remain difficult or slow? Where do AI-generated designs tend to break down?

Comments URL: https://news.ycombinator.com/item?id=46344509

Points: 2

# Comments: 5

Ask HN: Communities for Staff+ Engineers?

brihati — Fri, 19 Dec 2025 17:11:01 +0000

Besides HN, are there any communities where I can discuss an idea with peers?

Comments URL: https://news.ycombinator.com/item?id=46328227

Points: 2

# Comments: 1

New comment by brihati in "Ask HN: What are your predictions for 2026?"

brihati — Wed, 17 Dec 2025 06:22:37 +0000

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.

New comment by brihati in "Show HN: Dograh – an OSS Vapi alternative to quickly build and test voice agents"

brihati — Mon, 15 Dec 2025 05:21:58 +0000

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!

New comment by brihati in "Show HN: KV and wide-column database with CDN-scale replication"

brihati — Sun, 14 Dec 2025 12:38:13 +0000

Interesting, how did you come up with this idea? Have you tried it in production workloads?

New comment by brihati in "Ask HN: Do you write a technical doc first or just vibe code?"

brihati — Sun, 14 Dec 2025 09:18:12 +0000

I agree. have you tried any framework such as spec-kit by Microsoft to generate feature specs?

New comment by brihati in "Ask HN: Do you write a technical doc first or just vibe code?"

brihati — Sun, 14 Dec 2025 09:14:35 +0000

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?

Ask HN: Do you write a technical doc first or just vibe code?

brihati — Sat, 13 Dec 2025 20:13:44 +0000

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?

Comments URL: https://news.ycombinator.com/item?id=46257562

Points: 1

# Comments: 6

New comment by brihati in "Ask HN: What hard problems are still underexplored?"

brihati — Thu, 11 Dec 2025 11:36:18 +0000

What you say is what you get

New comment by brihati in "Ask HN: What hard problems are still underexplored?"

brihati — Thu, 11 Dec 2025 11:33:11 +0000

Is 2+2 still 4 :p

New comment by brihati in "Ask HN: What hard problems are still underexplored?"

brihati — Thu, 11 Dec 2025 11:30:54 +0000

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