Hacker News: camdenreslink

New comment by camdenreslink in "Claude Fable 5"

camdenreslink — Tue, 09 Jun 2026 18:22:40 +0000

People game benchmarks for fake internet points to get their favorite web framework to the top of the list. I'm pretty sure they will do it for billions of dollars.

New comment by camdenreslink in "LLMs are eroding my software engineering career and I don't know what to do"

camdenreslink — Mon, 08 Jun 2026 02:00:57 +0000

Even Python is very old (in programming terms), version 1.0 was released in 1994. Many here weren't born yet.

New comment by camdenreslink in "LLMs are eroding my software engineering career and I don't know what to do"

camdenreslink — Mon, 08 Jun 2026 01:13:51 +0000

Why would you create a homegrown port of Docker? Docker the container software, or Dockerhub the image repository? This is just confusing. If you didn't want to use Docker there is a perfectly good well tested alternative called Podman with wide adoption.

New comment by camdenreslink in "LLMs are eroding my software engineering career and I don't know what to do"

camdenreslink — Mon, 08 Jun 2026 00:49:14 +0000

> Any eng that is only using Claude Code or Codex or whatever, is frankly not entitled to talk about AI's limits since they are using the most basic harnesses. They literally don't know better.

I really doubt big tech has much better harnesses than are publicly available. Definitely not "catapult vs space travel". They have the same base models we all have access to.

New comment by camdenreslink in "LLMs are eroding my software engineering career and I don't know what to do"

camdenreslink — Mon, 08 Jun 2026 00:46:47 +0000

> Let's not pretend that someone with prior software skills will be able to produce larger scale and/or higher quality work compared to someone with no experience.

This seems like a really confident prediction. It isn't true right now, why do you think it will be true in the future? Right now having knowledge and experience is a huge benefit to steering the LLM (it makes dumb decisions all the time still).

New comment by camdenreslink in "My Software North Star"

camdenreslink — Mon, 08 Jun 2026 00:19:30 +0000

If an email address with a + symbol doesn't work then that is a bug because that is a valid email address.

New comment by camdenreslink in "Harness engineering: Leveraging Codex in an agent-first world"

camdenreslink — Sun, 07 Jun 2026 13:24:07 +0000

This hasn’t been my experience. State of the art models available to the public still do all sorts of bandaids and bad hacks. Putting code where it doesn’t belong. Stapling types onto variable (in TypeScript) when abstractions/types already exist to use. I use it to generate code, but still have to review every line and have corrections/steering basically every time.

Maybe you have access to some other model?

New comment by camdenreslink in "My Software North Star"

camdenreslink — Sun, 07 Jun 2026 12:46:35 +0000

There are some really obvious things that are definitely bugs. If login doesn’t work if your email address contains the letter “e” when the expectation is all valid email addresses should work, then that is a bug. It isn’t “indistinguishable from a feature”. If clicking a button in your accounting software consumes all the RAM on your computer and causes it to crash, then there is no universe or agreed upon definition that would consider that a feature instead of a bug.

New comment by camdenreslink in "Uber's $1,500/month AI limit is a useful signal for AI tool pricing"

camdenreslink — Thu, 04 Jun 2026 17:44:07 +0000

There are a lot of instances where you don't want to create an abstraction that will tie two disparate areas of the code together even if they happen to be using a similar pattern you want to copy. For example, when you expect their implementations to diverge in the future.

I have experienced enterprise codebases that have been DRY'd to the point they become ossified.

New comment by camdenreslink in "AI has a multiplying effect on existing technical skills"

camdenreslink — Sat, 23 May 2026 12:26:11 +0000

Gell-Mann Amnesia effect in action

New comment by camdenreslink in "Was my $48K GPU server worth it?"

camdenreslink — Fri, 22 May 2026 13:37:34 +0000

I believe they also excluded stock-based compensation from their calculation, which could easily tip them in the non-profitable direction.

New comment by camdenreslink in "What Is Happening to Publishing?"

camdenreslink — Thu, 21 May 2026 20:35:41 +0000

The low budget marketing channels that worked in the past are harder in this post-LLM world. SEO seems to have changed a lot, email marketing now involves trying to escape the Promotions tab, organic social media marketing is much harder too (I suspect the large social networks want you to buy ads, not get organic reach as a person/business promoting a product or service). Marketing something like a self published book online has changed dramatically.

New comment by camdenreslink in "Rewrite Bun in Rust has been merged"

camdenreslink — Thu, 14 May 2026 12:58:03 +0000

Yea, what the heck.

New comment by camdenreslink in "If AI writes your code, why use Python?"

camdenreslink — Tue, 12 May 2026 02:15:26 +0000

If you were using Python, then probably not.

New comment by camdenreslink in "Software engineering may no longer be a lifetime career"

camdenreslink — Mon, 11 May 2026 19:27:33 +0000

If the AI slop software managed to get a user base, then you can't just throw it away and completely start over. You need to modify it in a way that is seamless for your users. If all code becomes single use, are users generating it for themselves? Do you think a dentist office will vibe code their own scheduling software?

New comment by camdenreslink in "A.I. note takers are making lawyers nervous"

camdenreslink — Mon, 11 May 2026 14:22:00 +0000

The AI note summaries in meetings I'm in are frequently totally inaccurate. They are actually inaccurate in two ways: they fabricate things that were never said (but always kind of close to something that was said), and they emphasize the totally wrong thing (e.g. acting like the entire conversation was about one topic when that was just a very small part).

I sincerely hope these aren't used in court.

New comment by camdenreslink in "I'm going back to writing code by hand"

camdenreslink — Mon, 11 May 2026 13:58:20 +0000

Writing tests against a bad implementation usually doesn't work well. In this scenario I would have an LLM look at the changes in the branch and try to create a markdown document of the changes, why it thinks they were made, etc. and then review that doc with the manager and do a new implementation from scratch after aligning.

New comment by camdenreslink in "I'm going back to writing code by hand"

camdenreslink — Mon, 11 May 2026 13:51:00 +0000

If you work on a product that has an existing user base that has an expectation that things will still work then you definitely still need to read the code. LLMs frequently break things or introduce subtle incompatibilities.

Maybe on projects with no users you can yolo things.

New comment by camdenreslink in "A recent experience with ChatGPT 5.5 Pro"

camdenreslink — Sat, 09 May 2026 13:22:27 +0000

Total volume of usage is not an advancement, it’s orthogonal.

New comment by camdenreslink in "OpenAI’s o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors"

camdenreslink — Mon, 04 May 2026 02:48:57 +0000

No? Can an AI examine a patient in the physical world?