Hacker Newsnew | past | comments | ask | show | jobs | submit | ramshanker's commentslogin

Yea, I have started using c++ for some of the stuffs previously used python for. When agents is doing the grunt work, better to go even closer to machine.

At this point, I haven't even read around 30% of the code base in my open source project. I know our works by my manual testing. AI keeps writing tests for itself, even though I don't explicity ask for it, and I am not complaining.

Care to share a link?


Engineering buildings with vibecoded software? Sign me up

I guess this is what you call software architecture

A simple framing for reference.

Electrical Grid Frequency:

50 Hz = 3000 RPM.

60 Hz = 3600 RPM.

So, for Gaming Monitors 144 Hz = 8640 Hz.


Maybe this is one of those topics to let an army of agents get loose.

Nothing to lose and a lot to gain.


This is also one of things that needs to be well optimized to be any useful. Army of agents may get an implementation, but not sure it will be actually useful, and I'm also not sure if optimizing that implementation is going to be easier than more well paced use of LLM where person actually understands what code is being generated.


You seem to contradict yourself. Army of agents doesn't mean the person doing that doesn't understand the code. And optimization is required no matter whether the bulk of the code is written by hand or by the machine. LLMs definitely make things actually doable where previously they were nearly impossible.


> Army of agents doesn't mean the person doing that doesn't understand the code

This is quite literally, objectively what it means lol. No human will ever seen it.


I'm not sure where you're getting the "objectively" from except from your self definition of what it means to let an AI agent work on a project.


A single agent can produce enough code that even a team human can't reasonably keep up with if properly reviewed. An army of agents, definitely not. Most of us this everyday at work. Some are ok with it some are not.

The way I see it, the people understand that software, somewhat similar to how most understand their cars - at a very high level -- there is wheel, steering, axles, engine, gas tank, you put petrol to run it etc etc. If it breaks down in middle of road, even with all the tools most wont likely figure out what's happening or fix the car, and eventually goto the mechanic.


Energy consumption and CO2 emission it causes is a pretty big lose


That CO2 will be emitted either way. We can choose though what % goes to funny cat videos and porn or useful open source code.


They build new data centers -> extra CO2

They build new power plants -> extra CO2

They built non-climate neutral power plants to power the data centers -> extra CO2

https://news.ycombinator.com/item?id=49223845

It’s not like we had some already produced spare energy lying around. Consumption went up, production went up, often it’s conventional production with CO2

There is a reason Google and MS scrapped their CO2 goals


This argument, while totally valid, will never halt the build out of data centers nor hamper the development of AI.


Run it with a self-hosted model on a gaming PC running off a solar panel and UPS.


Yes. Waiting for the Windows Version myseflf. RTX Spark Desktop.


I guess copilot needs all the help it can get?


I hope it brings the RAM prices down!


It certainly could in the long-term but the spec is still being finalized and realistically a few years away from being able to put a dent in the HBM memory market.


Same here. Late to agentic party. 1st month was Codex, 2nd Claude, already thinking 3rd will be Codex again! Since Fable will be gone soon.


For me the Best Pros is "That one random-internet-comment is a good usability improvement, ask LLM to do the small change and commit immediately."

Smaller ideas need not be approved, or held back by schedule pressure from bean counters. Just Do It. :). It's the small corrections which end up polishing the product as good as "professional usability studies".


Yeah, the small bits of sand in the gears is something that is hard to sell when you allocating engineering effort. But it adds up over time.

It makes the difference between a tool that is a pleasure to use and one that causes dread.


A team can do the same, it's based on management structure, not the existence of a team.


If they release a model comparable to OpenAI / Antropic, will there be any reason left for 1T valuation of other companies? At that point, it will simply become Revenue proportional to Gigawatts available. Whoever got the energy wins.


DeepSeek and friends already exists, yet $1T valuations still exist. I think we are nearing a point where inference and cost metrics become the primary optimization for a while. Both capacity and costs are going to drive it from the demand side. I've personally moved to open weights already, now setting up vendor calls to make them available at work.

Talking with OpenCode and Fireworks, appreciate any recommendations that have SOC-2 and the like


CloudFlare host the best models (Deepseek/Kimi)


They seem to be missing a number of them, DeepseekV4 did not show in their list / search. They seem to be slow on offering the latest options, a number of them are MIA


*best open models


I can count 2:

Dec 2025: We use a commercial 3D modeling software to build refinery. There was no license dashboard in this ancient piece of junk. Fortunately license server provided verbose live status report through a command line. I ask ChatGPT to ingest the logs into a Django web application and generate weekly/monthly/yearly usage dashboard, and It one shorted the whole Backend + Frontend in 4 to 5 shot. There were around 10 regexes just in the log parsing batch script. I was totally speechless. Encouraged by the success of, I went ahead and made the dashboard for 3 more software in the same Django app. Released to peers by evening, feedback incorporated in 2 days to integrate Name, Employee Number, IP Address sync etc in 2 days. And it’s been live for 5 months, actively being used by all coadmins, even management has it bookmarked, to help with department redistribution. Making this thing without AI would have taken well over a month of “learning new stuff”, or paying external consultants too much. Even head of IT replied back, it was awesome. ;)

2nd , June 2026: I asked codex to something fairly complex before going to morning bath!, which would have taken me more than a week of learning DirectX12 API nuances and such things, 20 min latter, I return to task exactly completed with code changes in 5 different files. Build complete without any error. OMG. Free Quota over for whole month! I subscribed by the evening.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: