HackerTrans
TopNewTrendsCommentsPastAskShowJobs

pramodbiligiri

1,786 karmajoined 19 ปีที่แล้ว
Consultant on big data and dist systems: https://www.pramodb.com

Twitter: http://twitter.com/pramodbiligiri

LinkedIn: http://www.linkedin.com/pub/pramod-biligiri/23/65a/b97

Email: pramodbiligiri AT (Google’s email service).com

Submissions

Harbor: Evaluate agents in sandboxed environments

harborframework.com
1 points·by pramodbiligiri·4 วันที่ผ่านมา·0 comments

Out of the loop

saturnino.substack.com
2 points·by pramodbiligiri·13 วันที่ผ่านมา·0 comments

The principle of least power (2007)

blog.codinghorror.com
2 points·by pramodbiligiri·18 วันที่ผ่านมา·0 comments

Zen of AI Coding

nonstructured.com
1 points·by pramodbiligiri·19 วันที่ผ่านมา·0 comments

TOML Schema

toml-schema.org
3 points·by pramodbiligiri·24 วันที่ผ่านมา·0 comments

How we built Cedar with automated reasoning and differential testing (2023)

amazon.science
2 points·by pramodbiligiri·25 วันที่ผ่านมา·0 comments

Show HN: Shipsmooth: coding workflow plugin for iterative, solo-dev work

shipsmooth.net
1 points·by pramodbiligiri·26 วันที่ผ่านมา·0 comments

Against essential and accidental complexity (2020)

danluu.com
1 points·by pramodbiligiri·26 วันที่ผ่านมา·0 comments

Harness engineering for coding agent users

martinfowler.com
4 points·by pramodbiligiri·เดือนที่แล้ว·1 comments

Harness engineering: Leveraging Codex in an agent-first world

openai.com
297 points·by pramodbiligiri·เดือนที่แล้ว·206 comments

Productivity effects across generations of AI coding tools [pdf]

nber.org
1 points·by pramodbiligiri·เดือนที่แล้ว·0 comments

The (lack of) cognitive load of readable code

nikkipin.ski
5 points·by pramodbiligiri·เดือนที่แล้ว·0 comments

open-spdd: Design Philosophy

github.com
2 points·by pramodbiligiri·เดือนที่แล้ว·0 comments

How to evaluate models for production coding agents

blaxel.ai
3 points·by pramodbiligiri·เดือนที่แล้ว·0 comments

A survey on Large Language Models for code generation [pdf]

dl.acm.org
2 points·by pramodbiligiri·เดือนที่แล้ว·0 comments

Sealed classes and interfaces in Java (2025)

baeldung.com
2 points·by pramodbiligiri·เดือนที่แล้ว·0 comments

Amdahl's law for AI agents

electric.ax
3 points·by pramodbiligiri·2 เดือนที่ผ่านมา·0 comments

Modern Web Guidance

developer.chrome.com
1 points·by pramodbiligiri·2 เดือนที่ผ่านมา·0 comments

Orchestrating AI code review at scale

blog.cloudflare.com
145 points·by pramodbiligiri·2 เดือนที่ผ่านมา·56 comments

Thermo-Nuclear Code Quality Review (Cursor Team Kit skill)

github.com
2 points·by pramodbiligiri·2 เดือนที่ผ่านมา·0 comments

comments

pramodbiligiri
·10 วันที่ผ่านมา·discuss
I feel that flow state[1] is possible as long as you don't feel distracted into doing other things and you're needed to guide the LLM along every few seconds/minutes (someone mentioned a pair-programming type tool in this thread). For me that works if you have a good spec + workflow tool (assuming you're doing interactive coding and not kicking off long running coding jobs). I feel that a good test of a workflow tool is that it should offload all bookkeeping from you, leaving you to just read the generated code and think about design/architecture.

I built one such tool for myself: https://www.shipsmooth.net. You can use it to spec/plan out a piece of work, and then easily keep updating the spec/plan as you churn through its implementation. The tool assumes that you will pretty much end up changing the spec/plan during implementation, based on how it's going. In general, I don't see how it's possible to one-shot high quality code for custom use cases.

[1] Going by the definition of flow state here: https://en.wikipedia.org/wiki/Flow_(psychology): "fully immersed in a feeling of energized focus, full involvement, and enjoyment in the process of the activity. In essence, flow is characterized by the complete absorption in what one does, and a resulting transformation in one's sense of time."
pramodbiligiri
·18 วันที่ผ่านมา·discuss
It's possible they are running at a loss at present. But in a recent podcast their founder said he believes inference is profitable, based on their experience serving models: https://newsletter.pragmaticengineer.com/p/opencode (search for "profitable")
pramodbiligiri
·19 วันที่ผ่านมา·discuss
https://archive.is/T1FJG
pramodbiligiri
·21 วันที่ผ่านมา·discuss
It would be interesting to see if LLM's can scan and surface such issues. Might have been probable with parsing tools pre-LLM also? Not sure.
pramodbiligiri
·23 วันที่ผ่านมา·discuss
I believe “sessionization” is a common term used for this: https://dev3lop.com/blog/sessionization-in-clickstream-event...
pramodbiligiri
·29 วันที่ผ่านมา·discuss
Fairly predictable given the times: a plugin for coding assistants that supports a development workflow that I like :) It's at https://www.shipsmooth.net/.

Perhaps the more interesting bit is that it's in Java (not Typescript or Rust)! Java 25 is pretty neat. Bonus: getting to know how to distribute a self-contained Java program using jlink and the likes: https://docs.oracle.com/en/java/javase/17/docs/specs/man/jli...
pramodbiligiri
·เดือนที่แล้ว·discuss
Yeah it was very disappointing that so few details were provided. One of the reasons I think it's going to be an open source project or effort that is going to show, sooner or later, how effective these things actually are.

In their podcast interview, they mention that it's an Electron app that users download, and so they periodically create a new build. See section "Autonomous Merging Flow" here: https://www.latent.space/p/harness-eng
pramodbiligiri
·เดือนที่แล้ว·discuss
There was one good analysis from that viewpoint recently: https://x.com/addyosmani/status/2059844244907696186
pramodbiligiri
·เดือนที่แล้ว·discuss
I'm not convinced of this bit: "it revealed three things as the real bottlenecks (1) deciding and specifying what to build, (2) verifying and being accountable for what is delivered, and (3) the deep human understanding — of the codebase, the business, and the environment — required to carry out both of these."

It could be that because coding was seen as expensive and a bottleneck, much effort (both upstream and downstream) had been going into making sure its input is correct and the output need not be discarded. If coding is seen as a quick and cheap step, its output could stand to be thrown away and therefore the same amount of oversight may not be needed upstream?
pramodbiligiri
·เดือนที่แล้ว·discuss
They seem to address that: "This is sharply different from occupations such as agriculture in which labor demand was famously decimated due to mechanization and automation. The difference is that the amount of calories people consume is relatively fixed — even a 25% increase led to the obesity epidemic — whereas the amount of software produced has grown a millionfold."
pramodbiligiri
·เดือนที่แล้ว·discuss
Google released "Modern Web Guidance" a few weeks back that includes a set of agentic skills: https://github.com/GoogleChrome/modern-web-guidance-src. I wonder if that includes some of the suggestions in this article.
pramodbiligiri
·เดือนที่แล้ว·discuss
Have you been interviewed by any of the top talk shows? Would love to see this discussed on Bill Maher, for example.
pramodbiligiri
·เดือนที่แล้ว·discuss
I hadn’t heard of libgit2. I wish more applications would expose library-style access, preferably available across different languages!

May not work for apps that want to launch their own threads and processes. But for almost everything else, I prefer function calls to launching processes, managing their lifecycle, communicating via stdout etc. If I wanted to do that, I’d be writing Bash ;)
pramodbiligiri
·เดือนที่แล้ว·discuss
How does one know that a website is "vibe coded"? Any good indicators?
pramodbiligiri
·เดือนที่แล้ว·discuss
Because I thought this is a good blog and more people should get to know. Found it by chance in some other thread: https://news.ycombinator.com/item?id=48414452.

Did the same with this Cloudflare one the other day: https://news.ycombinator.com/item?id=48276152
pramodbiligiri
·เดือนที่แล้ว·discuss
Have you been satisfied with the quality of code generated by the model? Or did you have to tweak some rule file or skill to improve it? Or is human-readable code not even a goal at this point?
pramodbiligiri
·เดือนที่แล้ว·discuss
This is a great interview! I had to switch from the transcript to watching it though - the transcript had many mistakes.
pramodbiligiri
·เดือนที่แล้ว·discuss
(OP here) The truth is much simpler. I mailed the mods and they bumped it up in the second chance pool [1] :)

1. https://news.ycombinator.com/item?id=26998309
pramodbiligiri
·เดือนที่แล้ว·discuss
As other commenters have clarified, it's about layering, separation of concerns etc. Goes by many names. One such terminology here: https://en.wikipedia.org/wiki/Hexagonal_architecture_(softwa.... DI frameworks use terminology like "Provider": https://en.wikipedia.org/wiki/Dependency_injection#Injectors
pramodbiligiri
·เดือนที่แล้ว·discuss
I agree with many of the points made by nimonian above (esp the one starting with 'make a single skill called "code" which describes the lifecycle'), based on my limited experience with these things.

I'm building a skill + CLI tool along those lines (for solo devs not corporates). Here is what my "lifecycle" type skill looks like right now: https://github.com/bitkentech/shipsmooth/blob/releases/dist/... (warning, heavily work in progress). You can see a demo here: https://shipsmooth.net/

I was not happy with the default code quality generated by Claude Code. So I've been adding some skill-file rules to address that, and so far happy with the results: https://github.com/bitkentech/shipsmooth/tree/main/skills/ex.... There was a similar one on HN yesterday called opencodereview: https://news.ycombinator.com/item?id=48406358

There are many such workflows out there! Matt Pocock gave a good talk about how he approaches it: https://www.youtube.com/watch?v=-QFHIoCo-Ko