The question is what is reasonable. This is more how I work for code and I just tried for a document.
i) Prompt (Human input)
ii) Response (LLM)
iii) For (i=0;i!=n;++i) {
iv) Review/adjust (Human input)
v) Response (LLM(s) - different perspectives) }
vi) Rewrite parts that failed/I am not happy with (Human input).
vii) Optionally repeat from iii.
This tends to get me somewhere I want. For code at least. I made a document with it recently (fairly concise) and still worried I'd missed some AI slop in it. Though there is always human slop if I just made it by myself.
Cutting coffee to just the morning definitely helped me.
My problem now is that if I think of anything vaguely interesting in the evening then my brain refuses to stop thinking about it. That and restless legs.
Evening if my main time for hobby projects so having them lead to disrupted sleep is really annoying. Any tips?
Magnesium, L-Theanine, and vitamin d. Make a regular bed time for yourself, and stop looking at screens 30 minutes before that time. Regular is more importantly than early, I.e. 11:30 is passable but only if it's always 11:30.
> Cutting coffee to just the morning definitely helped me.
I drink half a mug (~200 ml) at ~2PM. I drink black tea rest of the day. Used to drink 2L/day at some point (it was a controlled period which required that).
> My problem now is that if I think of anything vaguely interesting in the evening then my brain refuses to stop thinking about it.
Use a notebook to take notes or ooze it out from your brain and try to learn meditation maybe? I do both, and both helps a lot to me.
Also, if doing exercise is not a very good option, try yoga. Looks serene but makes your body work.
Black tea contains a considerable amount of caffeine too. Aside from that, I know of two people whose years-long mysterious health effects disappeared (one with stomach troubles and the other with bad muscle cramps) after stopping their all-day >1L black tea consumption. The tannins in tea bind to iron, so it might cause iron deficiency anemia (although studies yield conflicting results), which especially woman are already predisposed to, and for which iron deficiency tests are often calibrated towards men .
Tea contains significantly less caffeine, and its effect is mediated by other compounds in the tea. Basically, tea also contains a partial "antidote" to caffeine along with the caffeine
Let me clarify some of the points you have rightfully brought up.
As a disclosure, I hail from Turkey. We consume most tea per capita by a large margin, so we might have adapted to this. I don't know. I'm drinking tea regularly since I'm six, and my family is drinking considerable amount every day, too.
Let's start with iron deficiency which is the most widely touted side-effect. Regardless of the amount of the tea, I have never had iron deficiency or low-iron case in my life. On the contrary, I'm a type of person who wears t-shirt all year long, and generally pretty warm all-over. I mean, the room has AC on, and I also add a small desk fan to keep my cool right now. I'm not overweight either. Nobody from my immediate or larger family has low-iron case either (regardless of gender), and we all drink lots of tea, all day long. So there might be some genetics here.
Mayo clinic suggests that tea has "half the caffeine" of tea (I brew both) [0], however their effects on my body is wildly different. If I overshoot my daily coffee consumption, my heart rate increases and I feel the usual "tension" from high caffeine consumption. However, drinking ~2L of brewed tea doesn't do anything to me. Does not affect my sleep, anxiety levels or anything. It helps me concentrate, sure, but without all the bad side effects of coffee over-consumption. There's a paper about it, but it's sponsored by Unilever IIRC, so I won't share that.
Badly brewed, overly dark or stale black tea brews are not kind to the stomach. That's true. There's a kind of finesse to do it properly. From dosage to waiting times. Even if you do everything right, some people's body doesn't like tea, and that's alright.
Cramps? Now I'm hearing it for the first time, but I don't discount or dismiss it. It's just I never heard it from anyone around.
So while these effects might be true, these are not universal. I was sipping tea by 11PM yesterday and I was dead asleep at midnight, for example. If I have drank another half mug of coffee, I'd be watching sunrise probably.
Addenda: Human body can silently signal what it wants and what it doesn't. Sometimes I automatically stop drinking tea/coffee and switch to water for example. Listening to the body is essential to preserve its balance. Forcing it never ends well. Body is wiser than the mind.
I don't have any severe sleep problems, but I can relate to this issue. I find reading fiction helps. It's kind of difficult to dream about an interesting problem or a project, so the way I perceive the problem is that my brain doesn't slip into a narrative free-associative state. But if I can get myself to think about something "dreamable" then it's a different story. A book works b/c you already need to engage your imagination quite a bit as you read anyway
If you put your data in Snowflake then there is a built in AI (ok it’s Claude) that can access the databases. This sidesteps a lot of the issues in that the data is clearly already with Snowflake.
Having used codex a fair bit I find it really struggles with … almost anything. However using the equivalent chat gpt model is fantastic. I guess it’s a matter of focus and being provided with a smaller set of code to tackle.
Yes. If you haven’t yet read it Cory Doctorow’s new book Enshittification is well worth a read. I am still reading it but it certainly explains some of the bad practices by these major advertising/spying giants and the resulting market distortion. We need to up our game as technologists and hold our employers to account.
It was a strange decision to limit the drives. I can see they might want to accredit drives which would give a 'Synology Approved Experience', though outright only support their own was bizarre. I'm very pleased they are reversing this. Aside: Now we just need Apple to do the same and resume support for industry standard expandable memory and storage.
From my perspective it lined up exactly with when I was looking to upgrade. I decided to bite the bullet and go with Duplicati, storing to a European based S3 service. I decided against US cloud providers since the US is looking too politically unstable to put anything important there. It was easy to set up and so far is running well.
If you are interested in FPGA PCIe or PCI cards there are also a lot of Gidel boards available second hand. ProcSpark/ProcStar etc. The official software is proprietary and they often contain multiple FPGA devices so there is again an exercise working out the pinouts etc if you want to simply use them with Quartus. I got one with a massive Stratix IV on.
A Kintel UltraScale+ is quite a prize though, really nice write up.
The top-level Verilog module and Vivado .xdc file (contains pin mappings, timing constraints, etc) from Gidel for the HawkEye 20G-48. [0] No SDK from Gidel though.
My back burner project for them is to create a PCIe TLP sniffer/MiTM/device emulator by hooking up two together via 10 GbE for relaying TLPs with one of the remaining 10 GbE connection going to a host PC for the sniffed/injected TLPs. The Aria 10 FPGA PCIe hard IP allows for either root or endpoint mode so I “just” need to draw the rest of the owl, avoiding any Quartus IP modules that would make the setup non-transparent.
I’m not sure what using a 10 Gbit link for PCIe will be like with faster devices but fail0verflow got away with TLP proxying with 115200 baud UART. [1]
As a big openscad fan I love the idea of designing circuits with code.
I do wonder though about designing circuits vs designing schematics. I see you have ‘wire down 100’ making it a more visual language than defining the nets. Be interesting to separate the schematic layout from the nets, so rule base schematic layout can then be applied.
You can actually skip all the wire commands and still generate a valid netlist, however the schematic might be a bit hard to decipher if there are many components!
I did explore automated layout algorithms for components in the schematics, however the readability and flow of the schematics might not be ideal, depending on what the algorithm prioritizes.
In the end, I realized that the actual layout and arrangement of the schematic itself was critical in the overall understanding. That was when I decided to add the "wire" command and give more control back to the schematic designer.
In the future, I do plan to add some automated way to generate these "wire" commands for automated layout. If the designer ever chooses to edit this automated schematic layout, he would be able to edit the wire commands for finer control.
In the end, I do believe that the visual part of the schematic plays an important role in understanding it. I, too, have spent hours puzzling/being misled by poorly drawn/disorganized schematics. Especially during troubleshooting or creating an updated revision, having a good understanding of the schematic saves time.
One of the aims of Circuitscript is to make the visual part easier, so at least more time can be spent thinking and organizing the schematic itself.
I've had great results with Codex, though I found ChatGPT 5 was giving much better results than the existing model. So ended up using that directly instead. So very excited to have the model upgraded in Codex itself.
The main issues with Codex now seem to be the very poor stability (it seems to be down almost 50% of the time) and lack of custom containers. Hoping those get solved soon, particularly the stability.
I also wonder where the price will end up, it currently seems unsustainably cheap.
i) Prompt (Human input)
ii) Response (LLM)
iii) For (i=0;i!=n;++i) {
iv) Review/adjust (Human input)
v) Response (LLM(s) - different perspectives) }
vi) Rewrite parts that failed/I am not happy with (Human input).
vii) Optionally repeat from iii.
This tends to get me somewhere I want. For code at least. I made a document with it recently (fairly concise) and still worried I'd missed some AI slop in it. Though there is always human slop if I just made it by myself.