Hacker Newsnew | past | comments | ask | show | jobs | submit | cheevly's commentslogin

Oh no, my engineering profession requires me to use new engineering techniques due to advancements produced by engineering. Quality cringe.

It's not only that. If 1 person is able to d the job of 10 people. What do you think will happen to the other 9 people.

A company with 5 developers could potentially downsize to 3 developers using AI, while improving overall velocity. Would you agree?


No.


What about the type of user that uses thinking/reasoning to produce more advanced tooling in order to outsource more and more of their thinking and skillsets to it? Because I myself and many others that I know fall into that category.


Only if you naively throw AI carelessly at it. It sounds like you havent mastered the basics like fine-tuning, semantic vector routing, agentic skills/tooling generation…dozens of other solutions that robustly solve for your claim.


Gosh, I really should attend LinkedIn University of Buzzwords...


Yes, just buzzwords, totally no backing behind any of this. Your original comment makes so much more sense now.


This is so objectively false. Sometimes I can’t believe im even on HN anymore with the level of confidently incorrect assertions made.


You, uh, wanna actually back that accusation up with some data there, chief?


Compare models from one year ago (GPT-4o?) to models from this year (Opus 4.5?). There are literally hundreds of benchmarks and metrics you can find. What reality do you live in?


Comparing two data points gets you a line.

If you want to prove that there are not diminishing returns, you need to add at least one more data point in there.

You're really not showing any evidence that you even understand how this kind of math works, let alone that my statement is false.


Assets are the main bottleneck.


This post is grossly misaligned with the current state of the art. Sounds like they're talking about LLMs from a year ago.


Bro, go try GPT-3 right now. You are off your rocker. Good luck even getting it to stop repeating the same word indefinitely.


Skill issue. The below is an excerpt from some of my early notes from a project spanning 2020-2022 using the babbage model, not even davinci. This is pre-"chat" or instruction tuned models. I have many more notes, including more code generation, mermaid graphs, spatial reasoning, in context learning examples, examples of using it in agentic ways to write a medium size code project that worked, etc. I have these historic records and can tell you improvements have been minimal. Do you have any historical records or just vibes, feelings, and a lack of skill? I can confidently tell you that what has improved is size of model required to get decent output (smaller) and more importantly, operator skill required to get decent output (lower). Beyond that, it is same old.

In the below, lines which are questions were me, paragraph following was gpt3-babbage. No stop tokens used, just manually breaking off generation when it began talking as me.

---

how do mobile phones work?

Mobile phones work by connecting to cellular networks, which are made up of a series of cell towers that are spread out across a wide area. When you make a call or use data, your phone will connect to the closest cell tower, which then connects you to the wider network. This connection allows you to access features such as calling and texting, as well as data services such as web browsing and streaming.

how do cell towers work?

Cell towers are the infrastructure used in cellular networks to transmit wireless signals. They are typically tall structures that house antennas and other equipment that enable wireless communications. Cell towers work by receiving and transmitting wireless signals over a certain frequency, which is then picked up by mobile devices like smartphones. The tower then passes the signal to a base station, which then routes it to its destination.

how do wireless signals work?

Wireless signals are transmitted using radio waves. These radio waves are generated by a transmitter and then received by a receiver. The transmitter converts an electrical signal into an electromagnetic wave, which is then sent out into the air and picked up by the receiver. The receiver then interprets the signal and converts it back into an electrical current or data that can be used by the device.

what are radio waves?

Radio waves are a form of electromagnetic radiation with wavelengths ranging from as long as one meter to as short as one millimeter. Radio waves are used for a variety of communication purposes, including radio and television broadcasting, cellular phones, radar, and satellite communications.

what is electromagnetic radiation?

Electromagnetic radiation (EM radiation or EMR) is a form of energy release in the form of waves or particles that travel through space. It includes visible light, infrared, ultraviolet, X-rays, microwaves and radio waves. All of these types of radiation are produced by the sun and other natural sources on Earth.

what is energy in the context of electromagnetic radiation?

Energy in the context of electromagnetic radiation is the amount of work done by a photon, which is equal to its frequency multiplied by Planck's constant. It is also referred to as radiant energy and is closely related to intensity and power.

what is a photon?

A photon is a particle of light, which is an elementary particle that is the basic unit of all forms of electromagnetic radiation, including light. Photons have no mass and no electric charge and travel at the speed of light.

give me the formula for photonic energy in latex format?

$$\frac{hc}{\lambda}$$

explain this formula $$\frac{hc}{\lambda}$$This formula is used to calculate the energy of a photon. It is calculated by dividing the product of Planck's constant (h) and the speed of light (c) by the wavelength (λ) of the photon. The result is the energy (E) of the photon in joules.

write a python script that solves for lambda in this formula

```python # Import the math library to use sqrt import math

# Define constants h = 6.626e-34 # Planck's constant in m2 kg / s c = 3.0e+8 # Speed of light in m/s E = 4.5e-19 # Energy of photon in joules

# Calculate lambda using the formula lambda = hc/E lambda_val = (hc)/E

# Print the result print('The wavelength of the photon is {} meters.'.format(math.sqrt(lambda_val))) ```

write a python script that solves this formula

```python

def calculate_energy(h, c, λ): energy = (h c) / λ return energy

h = 6.626e-34 # Planck's constant in joules/second c = 3e8 # Speed of light in m/s λ = 500e-9 # Wavelength of the photon in m

energy = calculate_energy(h, c, λ) print("The energy of the photon is", energy, "joules.")

```


Do you not see the repetition here? You're literally proving my point. Yes, I know you can apply token penalties.


You need a year of practice.


Assets are very hard to produce and largely unsolved by AI at the moment.


There's AI based 3d asset generation tools around. For example https://www.meshy.ai/ https://hyper3d.ai/ https://www.sloyd.ai/


Today I learned all you need is some random 3d assets to solve for 'games need assets' problem.


This is definitely correct. I had a dream about a new video game the other day, woke up and Gemini one-shotted the game, but the characters are janky as hell because it has made them from whole cloth.

What it should have been willing to do is go off and look for free external assets on the Web that it could download and integrate.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: