teaearlgraycold's recent activity
-
Comment on Does anyone have any Nebula recommendations? I've just signed up! in ~tv
-
Comment on ‘I took two bites and had to spit it out’: US candy makers are phasing out real cocoa in chocolate in some products in ~food
teaearlgraycold Link ParentAs an unpaid brand ambassador for this company I highly recommend you try it. Very expensive and the price has gone up 50% in the last 6 years due to shortages. But it may be the best dark...As an unpaid brand ambassador for this company I highly recommend you try it. Very expensive and the price has gone up 50% in the last 6 years due to shortages. But it may be the best dark chocolate you ever have. Just get some bars and don’t bother much with the confections. Those are great as well but don’t let you appreciate the quality as much.
-
Comment on The first multi-behavior brain upload in ~science
teaearlgraycold Link ParentIt’s a nice piece of fiction. It is generally frowned upon to simulate human brains for eternities without their or their originator’s consent. This is also referred to as a “dick move”.It’s a nice piece of fiction.
It is generally frowned upon to simulate human brains for eternities without their or their originator’s consent. This is also referred to as a “dick move”.
-
Comment on The first multi-behavior brain upload in ~science
teaearlgraycold Link ParentI was thinking of this and figured one of the maxima would just be a really attractive woman.I was thinking of this and figured one of the maxima would just be a really attractive woman.
-
Comment on The first multi-behavior brain upload in ~science
teaearlgraycold (edited )Link ParentI personally don't believe insects to be conscious, but we're barreling towards an ethically complicated future. Still, very cool stuff. Without thinking of further iterations, it would be very...I personally don't believe insects to be conscious, but we're barreling towards an ethically complicated future. Still, very cool stuff. Without thinking of further iterations, it would be very interesting to test fly traps on simulated flies - rapidly iterating until you have the perfect trap. Or maybe do the same for mosquitos to curb malaria.
Edit: Now I want to write a sci-fi story where someone designs the perfect mosquito trap, hijacking their senses with a device created after billions of simulations with virtual mosquitos. Any mosquito within a couple of meters of it appears to be sucked in like a vacuum, but really they're flying directly at the device through no choice of their own. The appearance, shape, and scent of the object is perfectly tuned to cause your average mosquito to direct themselves into it.
-
Comment on What are people using instead of VS Code? in ~comp
teaearlgraycold Link ParentSwitch to Zed. Don’t get left behind.Switch to Zed. Don’t get left behind.
-
Comment on Survey reveals almost 50% of California teachers may quit teaching soon in ~life
teaearlgraycold Link ParentDon't go to court. Even readily complying a few times per year will be worth it.Don't go to court. Even readily complying a few times per year will be worth it.
-
Comment on Survey reveals almost 50% of California teachers may quit teaching soon in ~life
teaearlgraycold Link ParentSeems like the best option is still to take the phones and just accept some annual cost to holding them.Seems like the best option is still to take the phones and just accept some annual cost to holding them.
-
Comment on I don’t know if my software engineering job will still exist in ten years in ~comp
teaearlgraycold Link ParentIt’s more that if AI can do every part of my job then no person working from a computer is safe. It’s like planning for nuclear annihilation. As an individual, you don’t.It’s more that if AI can do every part of my job then no person working from a computer is safe. It’s like planning for nuclear annihilation. As an individual, you don’t.
-
Comment on I don’t know if my software engineering job will still exist in ten years in ~comp
teaearlgraycold Link ParentHow I would put it is that the "prompt" that I am given when I'm working professionally is insufficient for use by an LLM. I wasn't asked to make a WYSIWYG editor or define a DSL. But I quickly...How I would put it is that the "prompt" that I am given when I'm working professionally is insufficient for use by an LLM. I wasn't asked to make a WYSIWYG editor or define a DSL. But I quickly realized that without those functions it would be too hard to make something shippable. And if it was just a WYSIWYG then we'd be leaving the benefits of LLMs on the table. A little of both allows the user to use each for when they are most applicable.
LLMs help software engineers get more done while maintaining a higher quality bar. When I'm done writing code and want to take a break I can easily spend a few more minutes adding test cases I would have otherwise done without. I can get CSS hacks instantly that would otherwise have taken a lot of fiddling and StackOverflow to figure out. I can find implementation logic from a library in seconds to answer questions about how something will behave. The world needed so much more software than engineers had time to build. Now that we're faster why would we need less software?
-
Comment on I don’t know if my software engineering job will still exist in ten years in ~comp
teaearlgraycold Link ParentAt least in startup land I get extremely open-ended tasks like "I think our users want us to add a website-builder feature onto our AI phone receptionist app. Maybe do something like Claude...At least in startup land I get extremely open-ended tasks like "I think our users want us to add a website-builder feature onto our AI phone receptionist app. Maybe do something like Claude Artifacts?". And then you need to talk to users, see their current sites, ask them questions, and re-evaluate the assumptions in the task itself.
Given the above task I ended up doing something a bit different:
- Create a JSON DSL that builds a React webpage using a custom component library
- Use tool-calling LLMs to create the page. Constrain to the JSON schema built at runtime from the component library
- One tool to create a page from scratch
- One tool to identify segments to edit from a user's change request
- One tool to implement changes
- Implement a basic WYSIWYG page editor with drag-and-drop components, click-to-edit text, etc. Lots of little things are needed to get it good enough to ship.
- Make sure the sites support server-side-rendering for SEO
It's never just "Make the button blue and change the text". If that's your whole job then you're cooked right now. I have met people that consider themselves developers but probably could be (perhaps are?) replaced by today's LLMs. But a proper developer has so much to do that isn't just translating well-defined requirements into code, or whatever other tasks LLMs are good at.
-
Comment on Is it worthwhile to run local LLMs for coding today? in ~comp
teaearlgraycold (edited )Link ParentI just tried running Qwen3.5 27B @ 4b quantization on an M3 with 24GB. It loads. But it runs at 2.2 tok/s (slow). It can work with the Pi coding agent so I gave that a shot. After a few minutes it...I just tried running Qwen3.5 27B @ 4b quantization on an M3 with 24GB. It loads. But it runs at 2.2 tok/s (slow). It can work with the Pi coding agent so I gave that a shot. After a few minutes it was 50% through processing the 16,000 token agent prompt, at which point Pi killed the request to the LLM because it had taken too long. I guess for simple questions it might take 15-20 minutes to give an answer. You’ll definitely need one of Apple’s Max chips with 64-128GB of memory to do even half decent agentic tasks. The M5 series’ reported 4x prompt processing speeds sounds pretty appealing now.
Edit: I switched to Qwen3.5 35B-A3B @ 3b quantization. I can now actually get it to work with Oh My Pi. It's slow but it does work. It runs 7-12x faster than the 27B monolithic model from what I've seen. It's cool to see an agent running locally on a relatively low-end machine, tool calling and giving me a correct answer to a simple question.
-
Comment on Is it worthwhile to run local LLMs for coding today? in ~comp
teaearlgraycold Link Parent4bit is generally the optimal tradeoff from my testing. Yes you lose some quality, but you'll lose a lot more by going with a smaller model with more precision per weight.4bit is generally the optimal tradeoff from my testing. Yes you lose some quality, but you'll lose a lot more by going with a smaller model with more precision per weight.
-
Comment on Can coding agents relicense open source through a “clean room” implementation of code? in ~comp
-
Comment on Can coding agents relicense open source through a “clean room” implementation of code? in ~comp
teaearlgraycold LinkI don’t think you can call this a clean room implementation. The original code was almost certainly fed into the LLMs as training data.I don’t think you can call this a clean room implementation. The original code was almost certainly fed into the LLMs as training data.
-
Comment on Is it worthwhile to run local LLMs for coding today? in ~comp
teaearlgraycold (edited )Link ParentNot Apple’s. I’d recommend people buy Apple hardware now before their fixed pre-inflation contracts run out. For general consumers it’s hard to justify alternatives in the <$1,000 range. Edit: I...Not Apple’s. I’d recommend people buy Apple hardware now before their fixed pre-inflation contracts run out. For general consumers it’s hard to justify alternatives in the <$1,000 range.
Edit: I just noticed they’ve increased the starting prices on their laptops by $100-$200 this generation. You can still buy an M4 series laptop so I recommend that to any readers looking to save a bit of money.
-
Comment on Proton Mail helped US FBI unmask anonymous ‘Stop Cop City’ protester in ~tech
teaearlgraycold Link ParentYou can use bitcoin as well. But I really doubt bill serials would do much.You can use bitcoin as well. But I really doubt bill serials would do much.
-
Comment on Proton Mail helped US FBI unmask anonymous ‘Stop Cop City’ protester in ~tech
teaearlgraycold Link ParentMullvad accepts envelopes of cash with just your account number on them.Mullvad accepts envelopes of cash with just your account number on them.
-
Comment on Almost a third of Gen Z men agree a wife should obey her husband in ~life.men
teaearlgraycold Link ParentWell the question is: “A wife should always obey her husband.” I think it would be better to have the question be even more direct. Something like “A wife’s role is to be subordinate to her...Well the question is:
“A wife should always obey her husband.”
I think it would be better to have the question be even more direct. Something like “A wife’s role is to be subordinate to her husband”. I want to see the % of people that stand by that statement. A simple patriarchy test.
-
Comment on Is it worthwhile to run local LLMs for coding today? in ~comp
teaearlgraycold Link ParentThe M3 Ultra has pretty good bandwidth (820 GB/s) but limited compute compared to high end GPUs.people reported some success on Mac Studio's unified memory but due to the slower memory bandwidth it will be slower than proper NVIDIA setup
The M3 Ultra has pretty good bandwidth (820 GB/s) but limited compute compared to high end GPUs.
Atlas Pro is good and I watch his long videos to completion.