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.
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.
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.
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
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.
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".
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
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
https://youtube.com/@theclockstack
4 regions analog clocks running live 24x7.
USA, Europe, India, EastAsia
Currently FullHD, upgrading to 4K if it becomes slightly popular.
reply