justforfunhere

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.

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.

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.

[HUMAN-CODE] - code written by humans

[AGENT-CODE] - code written by Claude/Codex/Other agents out there

[HYBRID] - Combination of Humans/Agents

I would prefer to go through projects where people are writing code themselves. And this kind of tagging would help me filter through easily.

There must be other contributing factors too.

- Easily parsing UDS, ISO-TP protocol CAN frames

- Parsing CAN-DBC files

- Building CAN Frame Payloads based on messages in a DBC file.

Additionally, lets say I would like to write something new that I don't know anything about, I now go first to a LLM, or two of them, to get an idea of what would be the best approach. It saves a lot of time that would otherwise go in research and discovery.

But I still don't trust it enough to write production level code. When I am writing something that I know will be released in a product, I steer clear of LLMs.

All of this when I am doing my day job. For my side projects, I try not to use LLMs.

- Easily parsing UDS, ISO-TP protocol CAN frames

- Parsing CAN-DBC files

- Building CAN Frame Payloads based on messages in a DBC file.

This is really early stage. Any thoughts are welcome.

This is going to be a small side project which shall include utilities for working with automotive diagnostics and logging workflows.

I have to do a lot of this in my day job and that's where the idea comes from.

It made me think a lot what a normal Trisolaran conversation or exchange of information look like? How does a civilization evolve in this case?

There were certain apps which would give the user a lot of options to customize the lists and the items in them. Customize in ways that would make the TODO item the most unique TODO item in its requirement and its quality. Such apps made me think a lot. Or should I say, overthink a lot. I would spend a lot of time trying to find the ultimate, most specific, custom setting for a TODO item that would make it unique and give it a life of its own. Looking back now, I am not sure how useful it all was. Ultimately, I ended up doing some items and not doing others. I cannot quantify what additional productivity they brought to me.

Now I dont use any TODO app at all. I just try to remember things, and I don't feel any different from the time when I was using those apps. Makes me wonder! Was I trying to invent a problem so that I could use these apps as a solution.

Perhaps that's why so many people come back to the old plain paper or a simple text file approach. Perhaps we all realize that it was perhaps not a problem after all and we would still have achieved most of what we set out to do. And even if we didn't, in the end, it doesn't matter all that much because life still goes on regardless.

Having worked in this field, I can confirm that most such parts these days come with chip supported read/write protections for part of flash that contain the code. But even with no protections, I think that being able to modify embedded firmware is a feat in itself.

I am not sure how long will it take before you will not be able to buy a vehicle at all without having to consent to being monitored remotely 24x7, but it will happen sooner than later. And this coming from a developing country. Pretty sure it is much worse in the developed world.

I guess the market for second hand older vehicles might see an uptick because of this and might also see a boom in demand for expertise of maintaining and rejuvenating such vehicles.

Does anybody know what does this do behind the hood?

I will give your portal a try soon. Thanks

OP comes up with a problem that he is facing, only to be shown the other side of the story that he may have completely overlooked. It raises questions for OP and their organization.

This also shows that in such threads, on HN, people are more likely to empathize with the employee ( which seems quite fair in this case ).

Hopefully OP got some pointers that they can go ahead and work with.

Does anybody know what is the timescale we are talking about here? From start of inflation of Sun's outer atmosphere to engulfing of earth?

Whats your take on this? Do you feel happy or anxious or do not care?

To everyone who has commented here and even the OP.

You aren't really off the grid, imo.

Because you are still connected to the internet and writing comments here or blogs.

Go read Walden.