Hacker News: ttariq

New comment by ttariq in "An AI coding agent, used to write code, needs to reduce your maintenance costs"

ttariq — Wed, 13 May 2026 03:53:31 +0000

In my experience, the easiest way to reduce maintenance costs comes from better planning upstream (better task definitions, ACs, test coverage etc), and most important of all, it comes from giving the AI coding tools a shared context for the entire project that is a living artifact that grows with the project. In order to make that happen, we employ a single AI for the entire project (instead of each developer having their own) that is able to provide the right context to agents when they need it and update the context as each agent produces the output.

New comment by ttariq in "Vibe coding and agentic engineering are getting closer than I'd like"

ttariq — Thu, 07 May 2026 16:18:05 +0000

I am not sure about agentic engineering getting close to vibe coding, but I certainly buy into building trust in your agents, similar to how you would trust another team / colelague within your organization (the image resizing example), and the best way to make sure that a team is working well is to make sure the right context i available to them at the right time and whenever they change the code base, they update that "context." In the case of human programming, this context is in the form of architecture docs, tickets, product spec, ADRs, messages, code review comments etc and lives in a host of different places. It is also difficult to get humans to fetch and update the context with discipline. However, with agents, it is much easier to get them to consume the right context and keep it updated as they make changes to the code base. I think that is the key to making agents more reliable and being able to have the trust in their decision making and output. All of this, is of course, on top of standard unit testing etc.

New comment by ttariq in "Uber torches 2026 AI budget on Claude Code in four months"

ttariq — Wed, 06 May 2026 05:01:52 +0000

The token spend should really be seen against the output it created. I spent about 11k in tokens over a 40 day period (subsidized by the Max plan, of course -- I am not made of money), but the productivity in the period was insane. I was able to ship multiple fairly complex systems that are now working in production (document analysis system, resource management system, a complete re-architect of a healthcare system) plus loads and loads of experiements.

Looking at token spend in isolation is measuring productivity by lines of code.

How Data Science Predicted Brexit

ttariq — Thu, 30 Jun 2016 11:43:10 +0000

Article URL: https://www.linkedin.com/pulse/how-data-science-predicted-brexit-tayyab-tariq

Comments URL: https://news.ycombinator.com/item?id=12007844

Points: 3

# Comments: 0