S2D2

The reply it gave is complete nonsense, it didn't even use the dateutil method it's saying it did.

Nope. Great if it works for you but hopefully this exercise has proven care is needed and dont trust the code "AI" generates.

It added 37 lines to fix the time parsing and did indeed do so. It only needed one of those lines.

Thanks - it disappears on mobile due to the lack of space!

The first failure is incorrect timestamp parsing, i.e. it will throw an error. It's at this point no value is being added imo, far quicker to just fix the timestamp parsing than convince gpt it needs to. Then you can move on to the other bugs.

Personal highlight is how it's started cramming multiple env entries onto one line to get the line count down 😂. It still fails to parse the response in the same way as before.

Nope, yours is far, far worse. 222 lines 😂. It gets the right endpoint at least which mine didn't, then fails completely when it comes to parsing the response.

Dunno, the original prompt is gone. Here's one that spits out non-functioning code: Here's some info on data collection: https://help.openai.com/en/articles/5722486-how-your-data-is-used-to-improve-model-performance

I disagree, but I didn't use the exact same prompt so it could be pure coincidence. Not that comes to mind and I'm not logged in, so you could see what I do with a logged out session.

Apologies for the formatting and you'll have to sanity check the output for me!

This is no longer possible as it has seen my working code and will now produce a working example - you're welcome ChatGPT! Previously it accessed into JSON data using an invalid key and tried to store cumulative data as hourly totals (PV forecast from forecast.solar). The former is easy to spot, an outright error. The latter will look like it has worked but the values are nonsense, much more dangerous. I appreciate I'm being overly negative, it's a useful tool for getting started or finding relevant information but a lot of care is needed when using the output code.

To check I'm not talking nonsense I asked GPT-4.1 to replace a 30 line Python file I have to access a public API and store the returned data in a database. Took 10 minutes to write and test. Given no context, it produces code that looks fine. It doesn't even vaguely work as it gets the API syntax (which is publicly documented) very wrong. Fixing it requires replacing many lines of code (which are now 56, not 30). Given my existing script, it rehashes it to 76 lines without adding value and introducing a few unwanted side-effects. When told what the problems are, the code works, because the meat of it is the existing code. When asked to improve some timestring parsing that was written in a hurry it happily introduces bugs whilst claiming it has been improved. It will get you 80% of the way there, but so will copy-pasting the documented example from your provider's readme. The rest is from you if you actually want it to work, at which point you might as well just write the code.

Sources like stack overflow, which helped software engineers to share knowledge on a platform immediately available to everyone. AI companies see that data as fair game, scrape it all and provide a more user friendly interface to obtain it. The end result is playing out as we speak, contributing posts to stack overflow are tanking and will dry up. No new data to feed the models, things go south fast as technology moves on.

A 15 minute youtube video or adafruit tutorial will get you further than 2? 4? 6? 10? Hours invested in telling ChatGPT it got it wrong again. If it can't point you to the content it's incorrectly regurgitating faster than your favourite search engine then what is it actually contributing?

Don't use ChatGPT for software.

I looked at this for my install, anything without convectors just has a lower heat output so has to be much larger. I couldn't make it work without them being silly big so had T21/T22 fitted. The thing to watch out for is most of the designer radiator sites will state the output @65C without telling you they're doing so, so dont assume its @50 and make sure you know what you're actually getting at your design temp. Adam (heat geek) actually fell foul of this for the install at his own house so its easily done if you're not fact checking what the sales blurb claims.

Is that G100 then? That does give you more options to use the excess. Mine is G98 and involves holding back battery capacity to take the excess generation on the DC side. Can be as complicated as you like, simple setback if you have loads of capacity or more complex control logic using solar forecast etc.

If you never generate more than your export limit, just charge to 100% and forget about it. Things are more complex if you do. You can still leave all the self use stuff in place which will reduce your overall import but not the price you pay. Immersion diverter doesn't make sense with a heat pump on cheap rate though, I'd be turning that off.

Is it a triple power 3, 5 or one of their others? No inverter model given but Solax use a dongle that plugs into the bottom of the inverter to feed data to the online portal. Have you knocked this when replacing the battery? Is the battery working fine according to the inverter, just not showing up on the online portal?

Should they have to? Regulations should handle it in the background, e.g. insist on a whole house CT clamp and dont let an EV charger push it over whatever the DNO tells you for your area. Joe public would never even notice, car is still plugged in when they get home and ready to go in the morning. There's already something coming through on this I think, new builds are set to avoid charging at peak times unless you untick the obscurely named setting well hidden from your average user.

As a carrot rather than a stick, I don't know which way the Belgian system was implemented though. Probably similar to UK ToU, a comparative carrot in the context of the soaring standing charge stick.

Dynamic pricing seems a much better idea.