HNHacker News
TopNewBestAskShowJobs

ghuntley

10,078 karma · joined May 1, 2009

contact via https://ghuntley.com
submissionscomments
ghuntley··on OpenAI’s Windsurf deal is off, and Windsurf’s CEO is going to Google
For the love of God, can we get a reboot of the Silicon Valley television show? Just on AI. Like when they wrapped it, they wrapped it on AI usage. So, it's got the perfect arc for a reboot that focuses perfectly on AI.
ghuntley··on A Emoji Reverse Polish Notation Calculator Written in COBOL
Expand and I'll build it.
ghuntley··on Everything around LLMs is still magical and wishful thinking
There’s citations to the facts in the links.
ghuntley··on Everything around LLMs is still magical and wishful thinking
Canva has seen a 30% productivity uplift - https://fortune.com/2025/06/25/canva-cto-encourages-all-5000...

AI is the new uplift. Embrace and adapt, as a rift is forming (see my talk at https://ghuntley.com/six-month-recap/), in what employers seek in terms of skills from employees.

I'm happy to answer any questions folks may have. Currently AFK [2] vibecoding a brand new programming language [1].

[1] https://x.com/GeoffreyHuntley/status/1940964118565212606 [2] https://youtu.be/e7i4JEi_8sk?t=29722

ghuntley··on Ask HN: What useful AI tools do you use every day?
Amp aka https://AmpCode.com. I’m one of the core engineers building it - happy to answer any questions. We built Amp with Amp. So I guess I rely on Amp ;)
ghuntley··on The z80 technique reveals the source code for Atlassian's 'rovo' AI assistant
https://ghuntley.com/z80
ghuntley··on A look at Cloudflare's AI-coded OAuth library
See also: LLMs are mirrors of operator skill - https://ghuntley.com/mirrors
ghuntley··on I dream of roombas: 1000s of automated AI robots that autonomously maintain code
With respect a lot has changed since 2020. I appreciate your replies. Your points are valid. There is a lot to be solved. There’s some stuff that should not be automated but there’s definitely some stuff that should.
ghuntley··on I dream of roombas: 1000s of automated AI robots that autonomously maintain code
> ChatGPT and Claude

Out of interest, have you built an agent? Experienced the power of 500 lines of code run in a loop with uncapped tool calls? It's a different experience and outcome to copy and paste'ing from a chat interface.

https://ampcode.com/how-to-build-an-agent

> You can optimize agents all the way down your conveyor belts, but none of it will replace the discretionary management of a human.

Concur! My personal goal is to reduce the amount of times I need to get down into the weeds so I can focus more on spending time with my kids.

> Having a thousand automated AI robots to maintain your code may be no more useful than a thousand chimps and typewriters to help you write Shakespeare.

Perhaps; time will tell. There's classes of activities that I do every day that right now could be automated through agents running with unlimited tool calls. Think about topics like Renovatebot. Like, why don't we have Renovatebot for that class of KTLO?

ghuntley··on LLMs are mirrors of operator skill
Understanding how to build an agent and how Model Context Protocol works is going to be, by my best guess, the new "what is a linked list and how do you reverse a linked list" interview question in the future. Sure, new abstractions are going to come along, which means that you could perhaps be blissfully unaware about how to do that because there's a higher order function to achieve such things. But for now, we are at the level of C and, like C, it's essential to know what those are and how to work with them.
ghuntley··on LLMs are mirrors of operator skill
Absolutely! I kind of hate the term "vibe coding" because of its associations with brain off. It is so important for an engineer to take accountability for what they ship.

Now to your ponderoo about libraries, something I've found that's really fascinating is I've really stopped using open source libraries unless there's a network ecosystem effect for example like Tailwind. But for everything else, it's much easier to code generate it. And if there's something wrong with the implementation, I can take ownership and accountability for that implementation and I can just fix it with a couple more prompts. No more bullshit in open source. Some person might not even be maintaining the project anymore or having to deal with like getting a pull request fixed or open source supply chain attack vectors related to project takeovers and all that noise. It just doesn't exist anymore. It's really changed how I do software development.

ghuntley··on LLMs are mirrors of operator skill
Thanks.
ghuntley··on LLMs are mirrors of operator skill
Exactly. One of my favorite things to do is to dump a code path into the context window and ask it to generate a mermaid sequence diagram or a class diagram explaining how everything is connected together.
ghuntley··on LLMs are mirrors of operator skill
Keen to read the research. Can you drop the link?
ghuntley··on LLMs are mirrors of operator skill
No, it is actually a critical skill. Employers will be looking for software engineers that can orchestrate their job function and these are the two key primitives to do that.
ghuntley··on LLMs are mirrors of operator skill
Ah, I wrote a blog post specifically about this. Some engineers are not going to make it. https://ghuntley.com/ngmi
ghuntley··on LLMs are mirrors of operator skill
See the tweet on workflow that I put in the post. No courseware, no bullshit, it's there. Have fun. The blog has plenty of guidance from using specs to creating standard libraries of prompts and how to clone a venture capital-backed company while you sleep.
ghuntley··on LLMs are mirrors of operator skill
Typo on my part. I completely agree. Back pressure is everything.

Edit: I've just updated the post.

ghuntley··on LLMs are mirrors of operator skill
Hey dude, it's been a couple weeks since we caught up for a zoom. Maybe it's three weeks now. Still keen to catch up again, dude. It's gonna be a little bit busy for the next couple of weeks. I've got two conference talks to do then I'm gonna be over in San Fran, but keen.
ghuntley··on My AI skeptic friends are all nuts
ditto - https://ghuntley.com/disclosures
ghuntley··on A flat pricing subscription for Claude Code
This is me - speak soon. https://www.linkedin.com/in/geoffreyhuntley
ghuntley··on A flat pricing subscription for Claude Code
the new Claude code “max plan” would last me all of [1] 5mins… I don’t get why people are excited about this. High powered tools aren’t cheap and aren’t for the consumer…

[1] https://www.youtube.com/live/khr-cIc7zjc?si=oI9Fj33JBeDlQEYG

ghuntley··on AI Coding assistants provide little value because a programmer's job is to think
> Every single business that has a need for SWEs will obligate their SWEs to use AI coding assistants by the end of 2026, if not by the end of 2025.

Exactly why I authored https://ghuntley.com/ngmi - it's already happening...

ghuntley··on What If We Could Rebuild Kafka from Scratch?
I'm going to get downvoted for this, but you can literally rebuild Kafka via AI right now in record time using the steps detailed at https://ghuntley.com/z80.

I'm currently building a full workload scheduler/orchestrator. I'm sick of Kubernetes. The world needs better -> https://x.com/GeoffreyHuntley/status/1915677858867105862

ghuntley··on OpenVSX, which VSCode forks rely on for extensions, down for 24 hours
you are correct. vscode (mit) is utterly evil - see https://news.ycombinator.com/item?id=43786380
ghuntley··on OpenVSX, which VSCode forks rely on for extensions, down for 24 hours
Thanks for the share. Yeah, building upon VSCode (MIT) is a stupid idea. Regarding OpenVSX, it was developed whilst I was at Gitpod and transferred to the Eclipse Foundation. It's been many years now, so my memory might be a little dated as to what came first, but OpenVSX/Gitpod/Thiea/Eclipse origins can all be traced back to https://www.typefox.io/.

Anyway. OpenVSX is classic XKCD https://xkcd.com/2347/ territory—run by a small crew of brilliant volunteers, but the entire world depends/freeloads upon them.

ghuntley··on Getting forked by Microsoft
See also https://isdotnetopen.com and https://ghuntley.com/fracture
ghuntley··on Claude Code: Best practices for agentic coding
The industry has tried that, and the problems are well known (timezones, unpredictable outcomes in terms of quality and delivery dates)...

Delivery via LLMs is predictable, fast, and any concerns about outcome [quality] can be programmed away to reject bad outcomes. This form of programming the LLMs has a one-time cost...

ghuntley··on Claude Code: Best practices for agentic coding
Honestly, I don't know what to make of it. Stage 2 is almost complete, and I'm (right now) conducting per-language benchmarks to compare it to the Titans.

Using the proper techniques, Sonet 3.7 can generate code in the custom lexical/stdlib. So, in my eyes, the path to Stage 3 is unlocked, but it will chew lots and lots of tokens.

ghuntley··on Claude Code: Best practices for agentic coding
I will shortly; am building a serious self-compiling compiler rn out of an brand-new esoteric language. Meaning the LLM is able to program itself without training data about the programming language...
← PreviousPage 3 of 25Next →