Author Topic: Claude designs a 1 ohm standard resistor, how would you do it?  (Read 1094 times)

0 Members and 1 Guest are viewing this topic.

Offline aronakeTopic starter

  • Frequent Contributor
  • **
  • Posts: 518
  • Country: se
I had some reasoning back and forth with Claude on how to build a 1 ohm standard resistor.

Claude come with quite many good ideas. Like process on how to "dry" oil with sieves, include sieves in the box to continue to keep oil dry, what epoxy to use, calculations on thermal mass for different material, physical build etc. Claude quite frequently search eevblog and xdevs to figure things out.... Its quite impressive, but some human guidance still needed which I provided.

The build idea is basically to build a giant DIY 1 ohm Vishay VHA518-11. 15 well dried out 15.2 ohm S102K + some trimming resistors kept in a sealed cast aluminum box filled to 80% with medical grade paraffin oil. Then put this in another cast aluminum box with some insulation in-between and terminals on this box.

I have scanned 45 15.2 ohm resistors for TC, so that is done. Some of the other components I have and other are on the way from taobao.

Any "human" though on the design?

There are lots of 10K standard resistor builds presented here on EEVblog, but not many 1 ohm. So if someone have builds to share, that is also of interest.

Below from the Claude generated document. More in the attachment

Executive summary:

Purpose and Performance Target

This document describes the design and build of a homebuilt 1Ω precision resistance standard based on a parallel array of 15 Vishay S102K bulk metal foil resistors. The design targets sub-0.1 ppm/°C temperature coefficient and long-term stability in the ±0.5 ppm/year range — performance comparable to a commercial working standard such as the Fluke 742A or ESI SR104. The primary application is as a transfer standard for precision resistance calibration using an HP 3458A multimeter.

Build Philosophy and Key Principles

The design is guided by several metrological principles applied consistently throughout:
•   All-copper measurement path: bus bars, feedthrough rods, connecting cables, and solder (CdSn) are copper or copper-compatible throughout. Dissimilar metal junctions in the measurement path generate thermal EMF errors; eliminating them removes this error source entirely.
•   Kelvin 4-terminal connection: current and voltage paths are separated at the resistor field. Voltage sense taps are at the midpoint of each bus bar, not at the current entry points, ensuring bus bar resistance is excluded from the measurement.
•   Parallel resistor array: 15 individual S102K units in parallel. Individual unit TC values partially cancel, improving net TC by approximately −15 ≈4× over a single unit. Individual drift contributions also partially cancel, improving long-term stability.
•   Pre-selection and iterative trimming: all 40 available S102K units are characterised for TC before assembly. The 15 with the best cancelling TC combination are selected. After assembly, TC is verified by thermal cycling and individual resistors are swapped if needed. Two additional trim slots allow a higher-value resistor to be added to bring the final value to just above 1.000Ω.
•   Thermal isolation: a sealed oil-filled inner box (VT7) is surrounded by XPS foam insulation inside a sealed outer box (VT20). The effective thermal time constant of approximately 3 hours makes short-term bench temperature fluctuations essentially invisible to the resistor array.
•   Moisture exclusion: both boxes are hermetically sealed diecast aluminium with nitrile O-rings, neutral-cure RTV, and Araldite 2011 epoxy on all terminal penetrations. 3Å molecular sieve desiccant inside both boxes provides active moisture scavenging. The inner box has a nitrogen headspace. The outer box acts as a first moisture barrier before the inner seals.
•   Isothermal design: a copper base slab (100×53×5mm) under the resistor array provides an isothermal mounting plane. Combined with oil immersion, temperature differences across the array are minimised, which both improves TC measurement accuracy and reduces thermal EMF at solder joints.
•   Ratio measurement method: resistance is not measured directly on the 3458A ohms function. Instead, a stable voltage source drives current through the new standard and a Fluke 742A 1Ω calibrated reference in series. The 3458A measures the voltage across each resistor alternately. The ratio V_x / V_ref equals R_x / R_ref, so R_x = R_ref × (V_x / V_ref). This method cancels current source uncertainty and leverages the excellent linearity of the 3458A rather than its absolute accuracy.

Key Specifications
Parameter                                       Target / Value   Basis
Nominal resistance                       1.000 000 Ω           15× S102K parallel + trim resistor(s)
Temperature coefficient               < 0.05 ppm/°C   Pre-selection + iterative TC trimming
Long-term stability                      ±0.5 ppm/year   After 6-month stabilisation period
Thermal time constant              ~3 hours           XPS insulated double-box construction
Measurement method                      Ratio vs Fluke 742A 1Ω   3458A measures V_x/V_ref, R_x = R_ref × ratio
Measurement terminals              4-terminal Kelvin + GND   M4 copper rods through inner box wall, epoxy sealed
Bar dimensions                              85 × 15 × 2mm copper, 1.81mm gap   Parallel bars: 3.81mm lead pitch, holes 1mm from inner edge
Resistor slots                              17: 15 S102K + 2 trim   4mm hole-to-hole centres, single row
Temperature sensor                      Omega 44006 NTC 10kΩ β=3694K   In oil, 3.5mm mono jack on outer box
Layout                                      Inner box on one side, terminals on other   Short Cu cables cross insulation gap to outer binding posts
 

Offline aronakeTopic starter

  • Frequent Contributor
  • **
  • Posts: 518
  • Country: se
Re: Claude designs a 1 ohm standard resistor, how would you do it?
« Reply #1 on: June 21, 2026, 06:18:53 am »
i have 14 pieces of 10 ohm VHP101, VHP202Z etc, but even if choosing the 10 with lowest TC, i would end up with positive, TC so until I have found more 10 ohm sealed vishay resistors with low TC, building something similar with these will have to wait. Same with 10 ohm VPR221, have around 13 of these, but still too high net TC. I think 10 pieces of 10 ohm VPR221 would have been an interesting build.
 

Offline miro123

  • Frequent Contributor
  • **
  • Posts: 299
  • Country: nl
Re: Claude designs a 1 ohm standard resistor, how would you do it?
« Reply #2 on: June 21, 2026, 09:08:12 am »
Seems known procedure to build resistor standard.I want to mention mistakes that I made building it on this way.
 - 80% filed and hermetically sealed. - My sealing was  that standard AL case silicone rubber o-ring.  outside i sealed wit RVM - result after 2 years some minuscule leak appeared. in 3-th year leak becomes visible. I assume temperature variation causes some pressure.
My goal was to keep it for at least 20 years. Oil change for 1 ohm will not be an issue but in my case 10K.
Question.
DOe you need to measure hydroelectrical constant. Many modern DMM dont need it. E.g my Keythleys has option to  measure the 4wire sense voltage without current
 

Offline aronakeTopic starter

  • Frequent Contributor
  • **
  • Posts: 518
  • Country: se
Re: Claude designs a 1 ohm standard resistor, how would you do it?
« Reply #3 on: June 21, 2026, 09:55:20 am »
Great input!

Claude previously warned against silicone seal, and recommended nitril in the design document that should be quite a bit more oil resistant, slower aging and let through less water. I now pushed Claude a bit more on this topic, recommendation is Vitron/FKM/Fluoroelastomer, which is better in most ways. Then apparently there is FFKM (Kalrez, Perlast) which is very expensive. I now placed an order for some FKM.


Claude comments

Material comparison for your application
Nitrile (NBR/Buna-N) — what you currently plan

Good mineral oil resistance
Water vapour permeability: moderate — better than silicone but not the lowest
Long-term compression set: moderate — will slowly lose clamping force over years
Practical service life in static seal at room temperature: 10–20 years before noticeable relaxation

FKM (Viton) — the recommended upgrade

Excellent resistance to oils, considered very reliable in hydrocarbon service. Offers broader chemical and temperature resistance than nitrile. IET Labs
Water vapour permeability: significantly lower than nitrile — roughly 3–5× better
Hardness remains practically constant during ageing, unlike HNBR and EPDM which harden significantly — meaning FKM maintains its sealing contact force over decades IET Labs
Compression set resistance: excellent — best of any common elastomer at room temperature
Practical service life: essentially indefinite at room temperature in static application
Cost: 3–5× more than nitrile — but O-rings are inexpensive regardless IET Labs

FFKM (Kalrez, Perlast) — overkill but ultimate choice

Near-zero gas permeability
Essentially zero compression set
Used in semiconductor and pharmaceutical hermetic sealing
Very expensive — a single O-ring costs $50–200 depending on size
Genuinely worth considering for the inner box lid where seal integrity matters most over decades

EPDM — not suitable here

EPDM resists swelling in water-based fluids but is not suitable for hydrocarbon oils. It swells in paraffin oil — eliminate from consideration. IET Labs

Silicone — already discussed, avoid

High water vapour permeability — worst of the common options for moisture exclusion
 

Offline miro123

  • Frequent Contributor
  • **
  • Posts: 299
  • Country: nl
Re: Claude designs a 1 ohm standard resistor, how would you do it?
« Reply #4 on: June 21, 2026, 10:27:03 am »
Thanks for the feedback.
I wonder how your Claude chat session compares Paraffin vs silicone oil filling. It is worth mentioning that my10k an 2k resistors are filled with clean silicone oil HV electrically certified. High viscosity 320cT@40C
 

Offline aronakeTopic starter

  • Frequent Contributor
  • **
  • Posts: 518
  • Country: se
Re: Claude designs a 1 ohm standard resistor, how would you do it?
« Reply #5 on: June 21, 2026, 01:43:25 pm »
Thanks for the feedback.
I wonder how your Claude chat session compares Paraffin vs silicone oil filling. It is worth mentioning that my10k an 2k resistors are filled with clean silicone oil HV electrically certified. High viscosity 320cT@40C

Cut and paste below on Claude's view on liquid paraffin vs silicon oil.

Executive summary, both are fine and similar. As I plan to put some sieves in my resistor for long term extra dry oil, liquid paraffin seems to have a slight advantage.

"Liquid paraffin" goes under many different names depending on use and some very slight variations: white oil, Mineral oil, Transformer oil (typical lower purity). The more common name for metrology use would probably be white oil or mineral oil. For pharmaceutical purposed often Liquid paraffin, and it seems that is typically the purest kind, so i just happened to continue to use that expression.

Flukes "bath guide":
https://media.fluke.com/df74e46c-7444-4c40-b21e-b3190159b463_original%20file.pdf

and "how to select a calibration bath fluid" guide
https://media.fluke.com/4682a306-784f-4664-984c-b2e6009311e5_original%20file.pdf

give some more limited insight. It seems silicon oil is aviable in more different versions for wider temperature coverage.

------

how would you are using medical grade liquid Paraffin vs silicone oil?

9:23 PMClaude responded: Good comparison to make before committing to the fill medium.Good comparison to make before committing to the fill medium.
Medical grade liquid paraffin — your current planSearched the webSearched the webGood question — worth comparing properly before you fill the box.
Key properties comparison
PropertyMedical liquid paraffinSilicone oil (PDMS)Thermal conductivity~0.13–0.15 W/m·K0.10–0.16 W/m·K depending on viscosity Hammond Mfg.Specific heat~2.1 J/g·°C~1.5 J/g·°C (roughly 1/3 that of water)Density~0.85 g/cm³~0.93–0.96 g/cm³Volumetric thermal mass1.79 J/cm³·°C~1.4 J/cm³·°CViscosity stability with temperatureModerate variationVery low viscosity-temperature coefficient — changes very little with temperature Don AudioChemical stabilityGood at room temperatureExcellent — very high thermal and oxidative stabilityMoisture absorptionLowVery lowCompatibility with copperExcellentExcellentCompatibility with epoxyGoodGoodCompatibility with FKM gasketExcellentExcellentOdourOdourless (medical grade)OdourlessLong term stabilityGoodExcellent

Thermal conductivity — closer than expected
Silicone oil thermal conductivity is between 0.10 and 0.15 W/m·K for viscosities below 50 cSt, approximately 0.16 W/m·K above 100 cSt. This is actually slightly lower than mineral oil at comparable viscosities — the opposite of what many people assume. Silicone oil thermal conductivity is roughly one quarter that of water, and nearly the same as benzene and toluene. Hammond Mfg.Stompbox Layout
So the thermal conductivity advantage goes slightly to paraffin oil, not silicone.

Thermal mass — paraffin oil wins clearly
Silicone oil has lower specific heat (~1.5 J/g·°C) and slightly higher density than paraffin — giving volumetric thermal mass of roughly 1.4 J/cm³·°C vs paraffin oil at 1.79 J/cm³·°C. Paraffin oil has about 28% more thermal mass per unit volume — meaningful for buffering short-term temperature fluctuations.

Where silicone oil is genuinely better
Silicone fluids can maintain chemical stability at temperatures exceeding 200°C — mineral oils tend to oxidise and degrade at elevated temperatures. For your room temperature application this advantage is irrelevant. Don Audio
Silicone fluids have a low viscosity-temperature coefficient — viscosity changes very little with temperature variations. This means convective circulation inside your box is more consistent across the 15–30°C cycling range. A minor but real advantage during thermal cycling. Don Audio
Silicone oil is also cleaner to handle — less tendency to leave residue, easier to clean up if spilled.

Moisture absorption
Both are very low. Silicone oil is slightly more hydrophobic than paraffin oil — marginally better at resisting moisture absorption from residual headspace humidity. The difference is small and your molecular sieve handles this regardless.

One concern with silicone oil — molecular sieve interaction
Silicone oil (PDMS — polydimethylsiloxane) contains silicon-oxygen bonds. Some grades contain trace low-molecular-weight cyclic siloxanes (D4, D5) which can potentially interact with zeolite molecular sieve pores. This is well documented in industrial contexts where silicone contamination of molecular sieve beds reduces capacity over time. For your application the quantities are tiny and pharmaceutical grade silicone oil has minimal cyclic siloxane content — probably not a practical concern but worth noting.

What commercial resistance standards use
The ESI SR104, Fluke 742A, and Ohm-Labs standards all use mineral oil — typically transformer oil or similar. This is the established choice in the metrology community. Silicone oil is used in some temperature bath applications but is less common in sealed resistance standards specifically.

Honest recommendation
Medical grade liquid paraffin is the better choice for your build for these reasons:

Higher volumetric thermal mass — better short-term temperature buffering
Equal or slightly better thermal conductivity
Established use in commercial resistance standards
No cyclic siloxane concern with molecular sieve
Easier to source in pharmaceutical grade with guaranteed purity
Less expensive

Silicone oil's main advantages — high temperature stability and viscosity consistency — are largely irrelevant at room temperature in a sealed static application. Its lower thermal mass is a genuine disadvantage for your purpose.
Stick with medical grade liquid paraffin BP/USP as planned.
 
The following users thanked this post: miro123

Offline Conrad Hoffman

  • Super Contributor
  • ***
  • Posts: 2264
  • Country: us
    • The Messy Basement
Re: Claude designs a 1 ohm standard resistor, how would you do it?
« Reply #6 on: June 22, 2026, 07:54:25 pm »
The HP 4815a vector impedance meter used an oil-submerged oscillator capacitor. This solved humidity and, probably, barometric pressure problems. They chose an oddball oil, polybutene. Curious what Claude thinks of that?
 

Online Smokey

  • Super Contributor
  • ***
  • Posts: 3802
  • Country: us
  • Not An Expert
Re: Claude designs a 1 ohm standard resistor, how would you do it?
« Reply #7 on: June 22, 2026, 09:39:20 pm »
SmokeyGPT says the best way to get a 1ohm standard resistor is to buy it on ebay for $85
https://www.ebay.com/itm/277295194825
 

Offline aronakeTopic starter

  • Frequent Contributor
  • **
  • Posts: 518
  • Country: se
Re: Claude designs a 1 ohm standard resistor, how would you do it?
« Reply #8 on: June 23, 2026, 02:22:07 am »
The HP 4815a vector impedance meter used an oil-submerged oscillator capacitor. This solved humidity and, probably, barometric pressure problems. They chose an oddball oil, polybutene. Curious what Claude thinks of that?

Good suggestion! It seems polybutene have some advantageous properties, but the disadvantage that it its a bit less viscous, so less effect of evening out temperature. Despite power in a standard resistor typically is low, i could see it being quite a bit higher

I also asked if polybutene would would be good for an oil submerged oscillator capacitor (see further down). This is supposed to be a great use for polybutene as it have high dielectric stability, low dielectric loss and the lower viscosity is an advantage as it absorbs shocks and keep condenser plates in place.

This was some new things I had no clue about so thanks for asking the questions and thanks to Claude for coming with an answer


----------

Q:how about using polybutene oil?


Interesting suggestion — polybutene is used in some precision applications but has specific characteristics worth evaluating carefully.

**What polybutene is**Interesting suggestion — polybutene has genuine advantages in some applications but specific issues for yours.

**What polybutene is**

Polybutene is a synthetic hydrocarbon oil made by polymerising isobutylene. Unlike mineral oil which is a mixture of naturally occurring hydrocarbons, polybutene is a pure synthetic with very consistent composition.

The structure and grade of mineral oil can vary depending on the origin of the crude oil from which it was derived, whereas polybutenes are synthetic substances and consequently their properties are within a very narrow specification range.

Polybutene is typically used in cable jelly compounds, cable insulation materials and cable oils.

---

**Properties comparison**

| Property | Liquid paraffin BP | Polybutene |
|---|---|---|
| Origin | Petroleum refining | Synthetic — isobutylene polymerisation |
| Composition consistency | Variable by crude source | Very consistent batch-to-batch |
| Electrical insulation | Excellent | Excellent |
| Chemical stability | Good | Very good |
| Moisture absorption | Very low | Very low |
| Thermal conductivity | ~0.13–0.15 W/m·K | Similar range |
| Viscosity range | Wide range available | Wide range available |
| Viscosity vs temperature | Moderate variation | More stable than mineral oil |

---

**The significant problem for your application — viscosity**

Polybutene is available in a wide range of molecular weights and the lower grades are liquid at room temperature. However even low molecular weight polybutene tends to be **significantly more viscous** than light liquid paraffin at room temperature. Typical low-grade polybutene viscosity is **100–500 cSt at 40°C** — far higher than light liquid paraffin at **15–35 cSt**.

This high viscosity means:
- Poor convective circulation inside your small sealed box — thermal gradients across the resistor array will be larger
- Air bubbles trapped during filling are very difficult to remove without vacuum
- Much harder to fill the box and wet all surfaces and solder joints completely
- Slow to equilibrate thermally after assembly

There are low-viscosity polybutene grades but these are less common and harder to source in small quantities in pharmaceutical or high purity grade.

---

**Another concern — long-term stability and outgassing**

Polybutene, being a polymer, can undergo very slow degradation over years — depolymerisation releasing trace isobutylene or other small molecules into the headspace. In a hermetically sealed box this could slowly contaminate the nitrogen headspace and potentially interact with the molecular sieve. Liquid paraffin being a simple saturated hydrocarbon mixture is chemically inert and does not depolymerise.

---

**Where polybutene genuinely excels**

- Cable filling compounds where it needs to stay in place and not flow — higher viscosity is an advantage
- Applications requiring very consistent batch-to-batch properties
- High voltage cable insulation where its consistent dielectric properties matter

None of these advantages apply to your sealed resistor standard.

---

**Bottom line**

Polybutene offers no meaningful advantage over medical grade liquid paraffin for your specific application, and its higher viscosity is a real practical disadvantage for filling a small box and achieving good thermal convection. The batch-to-batch consistency advantage of being synthetic is irrelevant since you are buying one bottle of pharmaceutical grade paraffin which is already tightly specified.

**Stick with medical grade liquid paraffin BP/USP** — it remains the best choice for this build.



----------------

Q: Apparently The HP 4815a vector impedance meter used an oil-submerged oscillator capacitor where polybutene is used. Could that be a good usage for polybutene?


Yes — that is a perfect application for polybutene and an excellent example of where its specific properties are genuinely advantageous over mineral oil.

**Why polybutene suits an oil-submerged oscillator capacitor**

**Dielectric stability**
An oscillator capacitor immersed in oil uses the oil as part of the dielectric environment around the capacitor plates. Polybutene's synthetic origin gives it extremely consistent dielectric constant (relative permittivity) — typically around **2.1–2.3**, very stable with temperature and batch-to-batch. Mineral oil dielectric constant varies more with temperature and between batches depending on crude oil origin. For a precision oscillator where frequency stability depends partly on capacitor stability, consistent dielectric properties matter directly.

**Low dielectric loss**
Polybutene has very low dissipation factor — meaning it absorbs minimal energy from the AC electric field. This is important for an oscillator capacitor operating at RF frequencies — any dielectric loss in the surrounding oil would damp the oscillator and affect Q factor and frequency stability. Mineral oil has somewhat higher dielectric loss than polybutene, particularly at higher frequencies.

**Viscosity is an advantage here**
Unlike your resistor standard where low viscosity is needed for convective flow, a capacitor immersion application benefits from **higher viscosity** — the oil stays in place, damps mechanical vibration of the capacitor plates, and reduces any microphonic effects on capacitance. A slightly viscous polybutene surrounding the capacitor plates acts as a mechanical damper.

**Chemical inertness to capacitor materials**
Capacitor plates and dielectric materials (typically mica, ceramic, or metallised film in a precision oscillator) need to be chemically stable in the oil for decades. Polybutene is extremely inert and does not swell or attack these materials.

**No oxidation products**
Polybutene's synthetic saturated structure means it does not oxidise to form acidic degradation products that could attack capacitor plate metallisation over years — a known long-term issue with some mineral oils.

---

**The HP 4815A specifically**

The HP 4815A Vector Impedance Meter uses a variable frequency oscillator covering 500kHz to 108MHz. At these frequencies:
- Dielectric loss in the oil becomes significant — polybutene's low dissipation factor is important
- Capacitance stability directly affects frequency accuracy — consistent dielectric constant matters
- The oscillator capacitor likely uses oil immersion to improve temperature stability of capacitance by reducing TC of the air gap with a controlled dielectric medium

HP's choice of polybutene over mineral oil for this specific application reflects exactly these considerations — it was a deliberate engineering decision for a high-frequency precision instrument, not just convenience.

---

**General rule emerging from this comparison**

| Application | Best oil | Reason |
|---|---|---|
| Precision resistance standard | Liquid paraffin BP | Low viscosity for convection, high thermal mass, proven in metrology |
| Oil-submerged precision capacitor | Polybutene | Consistent dielectric constant, low loss at RF, viscosity damps vibration |
| Transformer insulation | Mineral/naphthenic oil | High volume, low cost, established thermal performance |
| High temperature bath | Silicone oil | Thermal stability above 150°C |

Each oil has a domain where its specific properties make it the best choice. For your resistor standard liquid paraffin remains correct — and now you have a good example of where polybutene genuinely earns its place.

 

Offline 5U4GB

  • Super Contributor
  • ***
  • Posts: 1590
  • Country: au
Re: Claude designs a 1 ohm standard resistor, how would you do it?
« Reply #9 on: June 23, 2026, 08:57:13 am »
Quote
Claude designs a 1 ohm standard resistor, how would you do it?

Take the money I would have spent with Anthropic and use it to order one from Element14.

Is this a trick question?
 

Offline tszaboo

  • Super Contributor
  • ***
  • Posts: 9540
  • Country: nl
  • Current job: ATEX product design
Re: Claude designs a 1 ohm standard resistor, how would you do it?
« Reply #10 on: June 23, 2026, 06:39:17 pm »
I have the same problem at work.
People spend 10 seconds prompting a document several pages long. They don't even read it.
And then forward it to me to review it and correct it. Saying just "No" is very polite, I would say something rather rude tbh.
 

Offline 5U4GB

  • Super Contributor
  • ***
  • Posts: 1590
  • Country: au
Re: Claude designs a 1 ohm standard resistor, how would you do it?
« Reply #11 on: Yesterday at 04:23:35 am »
People spend 10 seconds prompting a document several pages long. They don't even read it. And then forward it to me to review it and correct it.

So get the AI to review and correct it for you. If they're sending you slop, get the slop extruder to clean it up for them, and then let them know what you did, along the lines of LMGTFY when someone asks you to find X for them.

"claude, generate a ten-page report on X" -> "claude, summarise this ten-page report in a single paragraph".
 

Online Smokey

  • Super Contributor
  • ***
  • Posts: 3802
  • Country: us
  • Not An Expert
Re: Claude designs a 1 ohm standard resistor, how would you do it?
« Reply #12 on: Yesterday at 04:49:43 am »
People spend 10 seconds prompting a document several pages long. They don't even read it. And then forward it to me to review it and correct it.

So get the AI to review and correct it for you. If they're sending you slop, get the slop extruder to clean it up for them, and then let them know what you did, along the lines of LMGTFY when someone asks you to find X for them.

"claude, generate a ten-page report on X" -> "claude, summarise this ten-page report in a single paragraph".

I read a spec document that was obviously written by AI recently.  The problem was that it was wearing it's "marketing" hat and not it's "engineer" hat and it promised all kinds of stuff that was essentially impossible to deliver.  I had a boss that used to act like that.  He would respond the exact same way to any customer making any technical request.  "We absolutely can do that!  We'll have it done in no time!" Pretty funny. 
 

Offline miro123

  • Frequent Contributor
  • **
  • Posts: 299
  • Country: nl
Re: Claude designs a 1 ohm standard resistor, how would you do it?
« Reply #13 on: Yesterday at 07:09:54 am »
As an engineer, I am always keen on new technology and how to use it in my daily work.
The main problems I experience with AI in the hardware domain are:

1. Trustworthiness of answers – I often don’t know when to trust the response. AI models tend to generate answers that aim to satisfy the user. For example, I asked the same question to Claude Flash 2.5 and clearly explained the type of silicone oil I was using. The answer claimed that silicone oil is superior and meets modern standards when used in a 1-ohm standard resistor application. Same LLM two prompts two answers, choose the one who you like the most.  :)

2. Limited hardware knowledge – Most models seem to be trained primarily on software-related data. They perform very well on common Python tasks, but are less reliable for hardware topics and lower-level languages like C/C+
 

Offline grx

  • Regular Contributor
  • *
  • Posts: 73
  • Country: fr
Re: Claude designs a 1 ohm standard resistor, how would you do it?
« Reply #14 on: Yesterday at 07:46:46 am »
why are we forced to read "claude" regurgitated slop which is obviously heavily plagiarized from eevblog and xdevs knowledge because there is no other place this machine could have gotten "inspiration" from? This design belongs to the members of these boards.

"claude" is not a person. it does not deserve to be treated as such. it is an abusive machine that steals everything and sells it back to you, while destroying the planet and stealing your jobs. There is no good in it.

What other red line do we need to cross to stop using it?
 


Share me

Digg  Facebook  SlashDot  Delicious  Technorati  Twitter  Google  Yahoo
Smf