Agentic coding notes

Join the discussion

• Hacker News
• OP's alt text makes it clear that by "Galapagos Island" they mean Vancouver. I assumed that this was some sort of local nickname, but all of the references to "Galápagos of Canada" I could find are talking about Haida Gwaii instead.
  by martey
• Yeah I was like “woa a PGConf on the galapagos, i gotta get my ass to one if those!”
  by skrebbel
• Nobody calls it that.
  by pluc
• I think it’s just a metaphor for being isolated from the wider tech community.
  by dan-robertson
• It's really coming down to "Do we want to subscribe to a human with a salary of many ~$10000(s) ", or "Do we spend 100(s)$ on an AI subscription"

  Even with it's issues, the latest models are going to disrupt the labor economics.

  by cognitiveinline
• On the other hand, you have many more humans to choose from than models, and they don’t change their character every few months.
  by layer8
• It’s going to even out on both eventually, the diffusion will be painful though.
  by baq
• There is a reasone we use left and right margin/padding.

  This blog is quite unreadable for 27/32" monitors.

  by zapnuk
• There’s a reason not to maximize your browser windows. How do you handle HN threads on that monitor?
  by layer8
• The point of a wide monitor for me is to have two 720 wide windows side by side, not a single gigantic 1440 window with impossibly long lines.
  by ornornor
• Toggle to "reader view" or resize your window. It is up to you and really isn't that hard.
  by Aldipower
• I've read a lot of comments about using AI for coding, and my experience has been very different.

  I work on large C++ applications used by international airlines. If this software failed, it would make national headlines.

  Claude Code with Opus 4.8 is great at handling the boring code I don't want to write myself. It gets it right almost every time.

  However I still review every change and test everything before committing.

  Trust, but verify.

  by deterministic
• Really interesting article but there's one thing I wanted to point out about the reasons for code review:

  > If a company were shipping bugs at, say, a hundredth the rate we were at Centaur while relying primarily on review to catch bugs, then I could see their point, but that's not what's happening at the typical software company where people don't want to move away from human review [there might be non quality (as in non bug rate) related reasons to keep human review, such as keeping a high bar for code quality or keeping the codebase human-understandable, which pretty much immediately stops being the case if you let a fleet of agents go wild on a codebase] because of the perceived risk of shipping bugs.

  I don't agree that the main point of a code review is quality assurance; there are other reasons that have more to do with team convergence and junior staff learning: https://www.embeddedrelated.com/showarticle/807.php

  by jason_s
• URL typo: "hange how he works](/productivity-velocity/)". (I make this kind of Markdown syntax error all the time and set up a lint for '](/'.)

  You should talk to https://www.mechanize.work/ for sponsorship/credits and about environments.

  by gwern
• I can agree with Dan on two things: LLMs do often produce incorrect results and that it's still useful for productivity when used in moderation. For me the wrong results actually cause some kind of ragebait response so I become much more motivated to learn more about the subject to actually generate correct response. After I've learnt the subject area enough I find I'm better off having LLM review my code instead of writing it.

  I haven't even begun to try to comprehend how to use fuzzing testing to improve the ability to find bugs, but it sounds really interesting. I've seen mutation testing to be very useful for finding gaps in tests, so I can only imagine that fuzzing + LLMs might produce insane results.

  by nasretdinov
• A lot of the crazy ideas seem to have melted away in the face of massive context sizes. Today, I can put roughly a megabyte of utf8 text into my system prompt before things start to get weird.

  That is a massive amount of information even if we are being sloppy with it. You can read The Hobbit and the first Harry Potter book cover-to-cover and still have room to spare. I would deeply struggle to develop a world model this detailed for any business. Anything that needs to get more specific than these narratives can be a SQL query tool into the data warehouse, grep over the codebase, MS graph API lookup, etc.

  Giving the business a balanced way to collaborate over this one shared model of the world is a new challenge I am beginning to engage with. I've also noticed that the world model will compound on itself in terms of self-detection of update opportunities. The more constraints there are, the more likely we appear to violate one.

  by bob1029
• > melted away in the face of massive context sizes

  If only. There is a huge difference between "Gives good responses/can easily spot things within N context size" and "Technically works but sucks within N context size", almost all models basically become cave-people once you go beyond 50% of the "supported" context size, meaning while they may technically work with 1 million output tokens, those last 500K tokens are gonna be massively "dumber" than the first 500k tokens.

  by embedding-shape
• You’re forgetting that keeping the context small is better economically and delivers better results.
  by stingraycharles
• I'd like to highlight a different part of the article:

  > In general, when I talk to software folks about testing, I'm coming from such a different place that they immediately look at me like I'm an alien, so let's talk about how we tested at this hardware company I worked for, Centaur, which informs my biases about how I like to work. Some of the things that we did that were or are unorthodox in the software world are:

  > Hired dedicated QA / test engineers, with testing being a first-class career path on par with being a developer - No code review by default - Virtually no hand-written tests - Constant testing via what programmers sometimes called property based testing, randomized testing, fuzzing, etc., although we just called those tests (hand-written tests were called "hand tests"). - Large regeression test suite (3 months wall clock to execute on compute farm) - No unit tests

  Anybody here tried that (or a similar) approach? Especially going all-in on property based testing and fuzzing with no unit tests.

  I tried that approach somewhere before and the initial results were promising, but ran into political issues so the idea was canned.

  by duckmysick
• The first thing I started wondering was "is this the same Centaur that comes up as 'CentaurHauls' on a CPUID (EAX=0)?"
  by bitwize
• I really wonder what "randomixed testing" looks like in practice. What is the measure of success/failure?

  I undrestand for fuzzing you have a very basic "doesn't crash" metric. Property based tests.... you gotta write properties for the PBTs to work on. What is the randomized testing hitting?

  by rtpg
• No code review by default goes against actual established evidence (there is little of this for software development practice) that code review is the best way to find defects.

  I always get the impression from using hardware and other anecdotes like this that it is rare for hardware companies to know how to do software development well because their core competency is hardware. In fairness, it is uncommon for software companies to know how to do software development well.

  Every form of testing has its value when done well and they are using several forms that most software developers don't use- probably helps make up for the lack of code review and unit tests. But if they incorporated code review and unit tests their software would likely be even higher quality.

  Property based testing is amazing, but it won't provide full coverage. Regression suites are amazing, but generally the most expensive form of testing in terms of time to write and maintain tests and time to run them.

  Today AI can crank out unit tests so its silly not to have them.

  by gregwebs
• I bake MCP tools into everything now, including doing screenshots. Any LLM can run just about every function, including resizing the window. I just watched Fabel 5 do a full usability test on a new project, copying the release cycle for my agentic terminal, relaunching the app like 20 times as it went, ensuring the move to a built and signed release was working. It installed the program like 5 times (something I do daily multiple times).

  I noticed map tiles were not working and started to tell it, but then all of a sudden they reappeared and checking the logs it had found the issue and autocorrected itself.

  The key here is feedback loops and systems annealing.

  As for Dan, my God I love this guy. Glad someone posted it!

  by kordlessagain