jareds

I must have been lucky in my career then, in my experience code review was much more then a five minute check followed by approval.

Where do you draw the line, and where does someone take final responsibility? I don't have an issue with allowing AI to do everything with limited to no human verification for hobby projects. I have an issue with allowing AI to write and ship medical device software with no human review. What's the middle ground?

Is this really something to be proud of? I make heavy use of AI, but for anything that is eventually going to production there's still a human reviewer. Based on this I assume Anthropic is shipping code with no human review? Is the future of our industry going to be oneshotting prompts with out manual code review and then having AI fix the bugs found in production buy customers? I'm not trying to be a Curmudgeon, but am I missing something?

Are there API's that provide simple information on if it's a good night for astronomy? I am totally blind, but would like to know when it's a good night for my kids to use there telescope. I don't use a Mac as my primary machine, and xasteria is not accessible.

Don't ruin this for me. As a blind developer WSL is amazing. Windows accessibility is significantly better then Mac in my experience. I use WSL, everyone else uses a Mac, and all the same tooling and scripts work identically.

As a blind software developer this looks interesting, but the output descriptions are not useful. I asked it "create a diagram for a rest api with a database, app server, and cache." The diagrams alt text was "609 / 100k tokens used" The text it returned was "Created a simple REST API architecture with three core components: a web app server, a cache layer, and a database. Organized them into logical tiers." If it can generate the diagram it would be nice if the alt text was a detailed description of the diagram.

I also am looking forward to Apple smart glasses. I use Meta glasses because thre useful since I'm totally blind. I'd much rather have on device recognission though if possible. I also trust Apple more then Meta. At least I'm technically enclined enough to realize I shouldn't wear them in the bathroom or bedroom. At least when humans look at my AI prompts there maily seeing food boxes or computer bios screens.

Ever since Be My Eyes introduced there AI features it's my understanding that there's been a lot less need for volunteers. I'm totally blind, and started using the app once they added in AI. It works great for for things like reading food labels after my kids have movved things around, determining if the tv has been left on, etc. I think I would use the volunteer feature if I still lived alone, but I don't.

Thanks for creating this. I'm blind so the $16 USB tester off amazon to sort through my drawer of cables is not an option. This will stop me from needing to buy a sbc just so I have something running Linux to test cables.

What's the current situation for coding with Local LLM's on decent hardware? I have an M3 Max with 64 gb of ram and am thinking I should start looking at Ollama and Opencode? Is this a useful stack for smaller personal projects?

I wasn't planning on buying one, but I'll add this to the list of app enabled coffee tech I refuse to buy. As someone who's blind I'm getting really tired of app enabled coffee equipment with no open source integrations or protocol documentation. Fellow also doesn't appear to make any effort to make there apps accessible. They have had there Aiden out for over a year and I still don't see any notes about accessibility in there app update. I'm not going to buy one and use the home assistant integration since that could break at any time. Luckily I'm more of a coffee drinker instead of espresso so the Ratio Four works well enough for single cups and half pots.

How long until the $10 Github Copilot subscription goes away? That was a great deal for my limited personal programming. The only reason I switched from it to Claude was to get coding and general ai in a single bill.

I just switched from the $10 Copilot subscription to a $20 Claude subscription to get general AI and coding in one bill. I guess I'll try out GPT Codex.

All I want is a reasonably priced subscription combining both coding AI and general AI in a single bill for non professional use that allows me to opt out of my data being used for training. Google limits history to 72 hours if you opt out of training even if you pay them $20 a month which rules them out for me. I guess I'm going to try the $20 chat gpt plan. At this point I am wondering if I need to accept that were moving to a token based model and get comfortable with opencode and manually switching models.

Does anyone have experience with this Braille embosser? I haven't found any reviews or testimonials for this, but that may be because it appears a lot of the development has been done in France instead of the U.S. I'm totally blind and am interested in it for producing Braille graphics, specifically as a way to get an idea of what a design I create using OpenSCAD will look like before 3d printing it. I can't justify $2000+ for commercial embossers that can print graphics for what is a hobby I'm not sure if I will stick with.

The issue I have with using LLM's is the test code review. Often the LLM will make a 30 or 40 line change to the application code. I can easily review and comprehend this. Then I have to look at the 400 lines of generated test code. While it may be easy to understand there's a lot of it. Go through this cycle several times a day and I'm not convinced I'm doing a good review of the test code do to mental fatigue, who knows what I may be missing in the tests six hours into the work day?

Thanks for the clarification, I can see banning disposable vapes but still allowing reusable ones.

Why do we need to ban these? I'm not trying to be contrarian, but why do some people appear to be for banning tobacco but not alcohol? I don't claim to have all the answers or even strong opinions, but if your going to ban one recreational drug with negative externalities you should ban them all. I'd much rather hear people's opinions then ask AI.

I've been blind since birth. When it comes to 2d things such as linear and quadratic graphs, shapes such as triangles, circles, squares, etc, I had no issues when the material was provided using braille graphics. I can't comprehend representing a 3d object in two dimensions. When I was in college I switched from Computer Science to Telecommunications the second time I failed calc ii. I just couldn't comprehend rotating a shape around the access of a graph to get a 3d shape. This may be something solvable by 3d printing, but that was not easily available when I was in college.

Is there a good place for easy comparisons of different models? I know gpt-oss-20b and gpt-oss-120b have different numbers of parameters, but don't know what this means in practice. All my experience with AI has been with larger models like Gemini and GPT. I'm interested in running models on my own hardware but don't know how small I can go and still get useful output both for simple things like fixing spelling and grammar, as well as complex things like programming.

I don't know how it works now, but in my case the Doctor had nothing to do with it. It's obvious I'm blind since I use a cane. I showed the person in charge of accommodations how bulky a braille printer along with all its paper is, and the noise it makes that's loud enough to wake anyone who may be trying to sleep in the same room. They granted me the accommodation since I had to use braille for math, physics, chemistry, and computer science. I think in some ways it's easier having an obvious disability. You can't hide it, and the only time people don't believe your blind when using a cane is at the bar on Halloween.

Why are frequent attendance exemptions granted? I'm totally blind and when I went to college my lack of attendance had nothing to do with the fact that I was blind and everything to do with the fact that I made poor choices like other college students. If I didn't have the mobility skills to get to class then I shouldn't have been granted an exception, I should have been told to get better mobility skills before going to college. I think the only time I asked for an attendance exemption was during finals week. There was a blizzard at the same time as one of my finals and the sidewalks and streets were not plowed. This made it incredibly dangerous for me to go to take the test. I just emailed explaining the situation and took the test the next day.

I didn't realize that using disability accommodations to get a single was so common. I used the fact that I was blind to get a single in the early 2000's. It may not have been strictly necessary, but I justified it by the fact I had an incredibly loud braille printer that took up a bunch of space. I didn't try to stack accommodations though, since I could walk as well as anyone else I didn't get preferential treatment when it came to location.

It's also useful if your blind, I know this from personal experience. The ability to recognize objects, read package labels, read bios and boot menus, etc has been very useful to me. Claiming that the only things it's good for is white collar work or battlefield targeting isn't accurate. In spite of how useful I've found it I'm not claiming it's going to be net positive, I have no idea how this will all turn out.

Where are these providers and do they offer batch processing? If they don't how does there cost compare to Gemini and OpenAI batch processing? For the hobby project I'm working on batch processing is a great fit. The only cost comparison tool I've been able to find is openrouter and it doesn't support batch processing for cost savings.

My major issue is that the IDE doesn't use the same hotkeys or similar interface to VS Code. This isn't necessarily a problem, but the fact that it's so different means the learning curve is absolutely brutal so it's not worth the effort for me to look at it. If there was a basic getting started tutorial that walked you through building a simple program, finding and fixing compilation errors, performing basic debugging etc, that was written from the perspective of a screen reader user that would be incredibly helpful. Something like this may exist, but if it does I haven't found it.

Thanks, I've starred the project so I can keep up with it. I don't currently have any plans to do anything with Kotlin but will look at this if I do in the future.

I'm rooting against Kotlin since it appears to be only usable with the JetBrains ide. I'm totally blind and Jetbrains tools are not nearly as accessible or easy to use as VS Code with all the Java extensions in my experience. At all the jobs I've had no one cared if I didn't use Idea, but considering it looks like there's no good VS Code tooling for Kotlin if I have to use Kotlin professionally it's going to be painful.

Extraordinary claims require extraordinary proof. AMD's processors got much better, more people started buying them, the stock went up.