That's classic HN showing off their privilege. But the golden era of tech is coming to an end. The industrialisation of software is about to begin. Many of the devs here will soon be getting a reality check
What they are actually saying is: "Because our OG product (leetcode style tests) is now obsolete, we can now jump on the leetcode hate trend and use that to sell our new product".
Imagine having a bunch of Claude agents doing time sensitive work and this happens and now a single human needs to pick up several 8k PRs authored by bots that can't talk to you now. Not sure how effective it would be to switch models using OpenRouter and the like given that, as the Earendil guys said, there is a lot of session detail that the provider doesn't share. The uptime is really going to cap their market penetration imo.
> Imagine having a bunch of Claude agents doing time sensitive work and this happens and now a single human needs to pick up several 8k PRs authored by bots that can't talk to you now.
8k diffs PR is incredible, is it even sane for a human to comprehend that much?
There has to be a name for such scenario were the handoff from Agent to Developer is so difficult, its not even worth pursuing but to instead wait until the Agent comes back online.
No matter how good of a developer you are, we are still constrained to our minds working memory. Lots of people I have spoken to are aware of this. Agents produce lots of diffs in a fast pace, our minds don't get the time to grasp the changed logic. And then, we an Agent is unavailable all of the sudden, say in the case of it being an outage or usage limit reached, the human now have to go through massive amounts of changes. They cannot continue as usual, there is a spike, they have to learn the new changes and grasp everything before they can continue towards the goal.
Never thought of it, but knowing that they encrypt reasoning is it possible that they share the decryption keys with other cloud providers like GCP Vertex / AWS Bedrock?
If you're not using Codex and Claude at the same time, you're missing out heaps. Even without outages, OpenAI models are great reviewers for Claude; and vice versa.
Other than trivial PRs; everything I do with Opus/Fable gets reviewed by Astra; and everything I do with Astra gets reviewed by Opus/Fable.
Using only models from a single vendor, is like testing your website/webapp only on Chrome.
For me, commits are the atomic block; and a good commit should be self-contained anyway; where no additional context is necessary. If an agent can't figure out what a commit is supposed to do, with only the commit title/description and diff, it's a bad commit, and this has always been true in software engineering. I do not pass prompts between the two ordinarily.
After claude or codex finishes a commit, I switch console tabs and ask the other to review it; with the commit ID. I often find it helpful to inject a bit of human knowledge, and callout any areas of attention I see from a quick skim. (But that could just be me wanting to not abstract myself away from software engineering that much :)
Sometimes, I do ask Codex to read my ~/.claude/; and vice-versa. But, generally, I try to keep as much knowledge (e.g. investigations, reports, deep dives) inside the git tree as possible; so that is not necessary.
I don't use skills, but I do have ~/.codex/AGENTS.md and ~/.claude/CLAUDE.md. These are high-level instructions for what (1) I consider readable, maintainable code and patterns, and (2) workarounds for empirically observed model behavior IOdon't like, such as Astra being a bit of a "over-correct over-validation nit-picker". I keep these human-authored, and update regularly based on what I find annoying.
I do all of this before I submit a PR; but of course, for trivial stuff (e.g. CSS changes, copy/string changes, etc), I don't bother.
My practices and workflows do change over time. Back in the ~Opus 4.5 days I'd often define a rubric/criteria in a markdown file, iterate with AI to improve it, and that's the "spec". I've stopped doing that since GPT 5.6; partly because models have gotten a lot better at understanding high level intent from the context; and partly because nearly all models these days feel 'gradermaxxed' when working like that.
Finally, consumer $100/$200mo subs get you _so_ far, I get a lot of value from both. I used to have multiple Claude subs for a while, but trying to 'get full value' made me work on projects just for the sake of it; so 2x$200/mo is my cap :)
There's far more than zero evidence, see https://arxiv.org/html/2402.08806v1 ; or the industry-standard practice of using multiple model families as LLM judges; or even 1P implementations https://code.claude.com/docs/en/advisor (which misses most of the benefit; since you want different model families, with different pretrains and posttrains).
Eh that’s about medical diagnoses. Not directly transferable. For regular usage, multiple models just make you feel productive but I bet they aren’t any more productive than just one.
Neither electricity, nor the Internet is provided by one or two organizations globally, both with a blast radius that quite often takes out all of their services.
Not sure how long the latter will remain true – centralization is well underway there; try not to think of Cloudflare too much...
Globally no, but in the US there probably at most 2 providers covering your area + 5G/LTE providers. Electricity - single provider in the area. So if your job is on-site, then entire company stops working when either goes out. You don't really care that another company on the other side of the globe or street continues working.
We already got used to "internal going down globally" when AWS was the main cloud provider. Now its 3, AWS, GCP, Cloudflare, but "portion of internet that you care about is down for the entire world" is a casual thing to happen now.
> You don't really care that another company on the other side of the globe or street continues working.
As somebody in need of a doctor, on a plane etc. I'd definitely consider it much worse if all hospitals, air traffic controllers etc. stopped working at the same time instead of just a local subset.
When I worked at one of the early paging and cellular companies, every company had phones and pagers on at least one or two competitors for the oncall folks - you can't get a call to fix your cellular network when you are down.
Likewise while at Google, they didn't let us put Google Voice numbers down as our oncall phone number. Some folks even had multiple phones on different networks as backups.
I'm sure they have either other SOTA models or open source models around to help if things to completely pear shaped.
It's pointless as the problem isn't technical. It's a human problem as it requires human supervision. A cage isn't good if no human is actually checking it.
It's symbiotic. Google has been aggregating data from these websites for years to serve as summaries in search, reducing traffic to the sites. More pernicious is AMP, where the site is basically copied to the Google server. This force websites to use AdSense and structure the content in certain ways. If a site doesn't want to use AdSense, or allow Google to summarise the site, it gets down-ranked in search. A death sentence. Further, Google's algorithms routinely promote spam because this is most profitable for Google. Hiding the important information 3/4 of the way down a 10,000 word article with a hundred different kinds of ads on the page. Since the "good" websites have to compete with these spam websites, they either adapt or give up monetisation.
One of the more horrifying stories to read was about [Code Yellow back in 2019.](https://finance.yahoo.com/news/google-2019-code-yellow-blurr...) Google's algorithms were getting too good. Users were finding what they wanted too fast. They'd type in their query, the first result was good, then the user would close the tab. For Google, this meant less ad revenue. They wanted users to stay on Google for longer. *So they chose to degrade the algorithm quality.* Users would have to click multiple links to find the information they wanted, and inside every link was ads served by Google. This is one of the pivotal moments in one of the worst cases of enshitification in software history.
>If you are product-driven, life is pretty good, and maybe has never been better
It has certainly been better for junior devs, mid devs, anyone looking for zirp era salary growth and supply demand ratios. For a senior code-adverse coaster looking forward to see his static salary get eaten by inflation, life has indeed never been better.
Yeah, at Corp, that makes sense. I was thinking more along the lines of scrappy startup silliness. "I am one person and I deal with any and all code to get my product built."
From that POV, has it ever been better, assuming you can rise to the top of an ever more crowded market?
> "I am one person and I deal with code to get my product my built."
From that POV, has it ever been better, assuming you can rise to the top of an ever more crowded market?
Building a product is easier now, same way making a photograph is easier now. Making a reliable and high income living out of it though, it looks increasingly uncertain.
In a world with abundant music and photography, just saying that you made your music using Reason/ProTools or you made your photograph with a Leica isn't enough. I believe the same will happen with software. Sales, product design, customer service and operational aspects like uptime will matter more than the software itself. Ironically, this is the kind of stuff the HN type highly dislikes.
> I believe the same will happen with software. Sales, product design, customer service and operational aspects like uptime will matter more than the software itself. Ironically, this is the kind of stuff the HN type highly dislikes.
Agreed. It's not even a new thing. They tried to teach me/us long ago, starting by putting it into words we might more easily understand, such as "Customer Development" lol.
When I realized that it was the sales guys that will have the power in the mid-term new world, I got genuinely upset. However, maybe they always had the power and I just didn't want to accept reality.
Now, I believe the most desired hire in the near future will be the PMM.
> A Product Marketing Manager (PMM) in tech is a strategic bridge between the product, sales, and marketing teams who defines who a product is for and why it matters.
A PMM with a tech background must be worth their weight in unobtainium at this point.
Anyone who has learned a language knows this anecdotally. The linguistic structures need to be marshalled by active cognition (editing and writing). Merely reading and watching is not enough.
The name is also much more engaging. As we all know, naming things is hard. While NearbyGlasses is simple and descriptive, it's not emotionally charged like ZuckOff.
There is a setting in the “Reminders” app where Siri will automatically categorize your reminders into certain categories. If you have a shopping list and you add chickpeas and red beans for example it might put them into a category of “pulses and grains”. I think the idea is you probably buy all the things in a particular category from the same kind of store (or the same section of a supermarket or whatever).
For me yesterday I needed to buy dishwasher rinse aid so when I added it to my shopping list siri put it into the “beverages” category, and when my wife on a different occasion asked me to buy some makeup remover for her siri put that into a “condiments” section.
I have not done anything (on purpose) to make the classification like this by mistraining it or whatever - it’s just been that bad out of the box.
reply