I am sorry, but this kind of comment has become too common on this site. It underestimates the kind of code a highly efficient human being coder is capable of writing and managing over a long period of time ( which is what is required in a real job, btw ).
The only thing that I think coding agents are better than good human coders is the ability to generate a lot of usable code in a shorter period of time.
But can they maintain it over a long period of time? I highly doubt that, given the evidence that I have with me. Coding agents under-perform quite often in my line of work. They overproduce and yet are not able to cover the given requirements.
Sometimes they do 100% of the given task, but miss a slight detail ( given clearly in the prompt ), that renders their product unusable. This quite often results in a complete rewrite - consuming more, guess what, tokens!!!
So anyone who thinks that right now, coding agents can replace human coders completely, is really not working with these agents long enough or hard enough.
Once you start demanding from agents the same quality of code and the added responsibility/liability that you would associate with a human code, you will sure see the difference and I can tell you that its a lot.
I work with Opus 5.5 and Codex Astra 6 on a wide range of projects and they are found completely wanting in certain situations where a human would be more trustworthy and produce better results.
When claude code became quite good, I became quite excited. I wanted to make sure that I consumed my full quota ( 5-hourly and weekly ). I was working on four to five different project at the same time. And it was excruciatingly painful after the initial rush wore off.
I went back to working on one project at a time to regain my sanity.
First of all, congrats on the launch. I have worked with many such products and this is something that is required. There is no one solution fits all in this domain. Each vendor has their quirks that. So this is overall a great problem to tackle and kudos to you for taking this up.
Could you elaborate a bit more on how this is different from Renode?
Also you are entering into a market that has well established legacy players. Most of the firmware is developed in China. How do you intend to make a space for yourself in such a scenario.
Thank you, and for sure market is very fragmented. Which is exactly why we are starting small and modelling deep with stm32 as our workhorse here. The quirks we are finding them everyday! I have seen mcu controller behaviour from neither errata nor datasheet and thats the beauty of field testing.
I think our biggest difference to renode is the silicon validation and our commitment to keeping our simulation honest. I have struggled to find simulators that people actually put the measured differences and that is the direction we will go. We haven’t put our silicon validation benchmarks public yet but we will in the coming months!
As for legacy players, they don’t fill the niche enough. Thats why we exist and as a startup can fill this niche for the people that need it, whether its china, or anywhere else.
You should read the report, it is interesting technically if you ignore the fear-mongering. It distributes the model's layers over multiple compromised devices.
And considering typical WAN latencies of 20+ ms, what’s the expected inference rate, 1 token per month?
Maybe I did something wrong or unaware about the tricks to make it fast, but last time I tried to play with exo and distribute processing over a few home LAN computers to see if I can run models that don’t fit my 3090, the penalties were brutal.
As a fellow Indian growing up in 90s, I feel you. I had my fair share of beatings from teachers in school.
There were cases where parents who found it challenging to control their kids, would encourage teachers to use physical force on them. Parents deemed it was school's responsibility to instill discipline in their children.
As far as I can recall, use of violence to control kids was pretty common back in the day, both at home and at school. I don't see that happening nowadays, though.
Please, yes. Half of the fun of being on HN was "Show HN: I made some random thing", which typically amounts to "look at what prompt I wrote" nowadays. I use agents every day, I'm not against it, but it completely changes the lens through which I view a project
Indeed as it helps to give more meaningful feedback. Somebody in [HUMAN-CODE] might appreciate suggestions on the code but not care as much about business whereas [AGENT-CODE] probably prefers the other way around.
Frankly, it's surprising that we'd even need to stipulate something like this. It would never occur to me to post to a "show us what you're cooking" thread with: "Look what I asked DoorDash to bring me!", but I guess that's where we are now...
AI is you being the director. Hey, I directed this movie != I acted in it, I edit it, I control the camera, I wrote the music. It equals I told others what to do and my judgements and decisions affected the final result. Same with making with AI. You direct. If you have taste and talent you direct a good result. If you have no taste nor talent you make slop. This is no different than in movies.
The only thing that I think coding agents are better than good human coders is the ability to generate a lot of usable code in a shorter period of time.
But can they maintain it over a long period of time? I highly doubt that, given the evidence that I have with me. Coding agents under-perform quite often in my line of work. They overproduce and yet are not able to cover the given requirements.
Sometimes they do 100% of the given task, but miss a slight detail ( given clearly in the prompt ), that renders their product unusable. This quite often results in a complete rewrite - consuming more, guess what, tokens!!!
So anyone who thinks that right now, coding agents can replace human coders completely, is really not working with these agents long enough or hard enough.
Once you start demanding from agents the same quality of code and the added responsibility/liability that you would associate with a human code, you will sure see the difference and I can tell you that its a lot.
I work with Opus 5.5 and Codex Astra 6 on a wide range of projects and they are found completely wanting in certain situations where a human would be more trustworthy and produce better results.