A local model tops 60 tokens/s max. Running it on the background means not being able to use on the task you are working on. When working on local hardware you cannot do concurrent requests. In deepseek for example you can have 100 agents running each getting at 120 tokens/s easily.
In local models you are limited by your own infrastructure.
I do concurrent requests just fine and they have no noticeable performance impact. Not all local hardware is equal. Also, humans have to sleep. Agents don't, so processing stuff over night and reviewing in the morning just gets more utilization out of what is already there.
With cloud agents I also process stuff overnight. But my gpu is limited. If I want to OCR a high number of documents or vectorize data, I can't run an LLM at the same time. I use remote models and use my compute for running commands on my desktop machine.
I am using Opus 5.5 high almost exclusively. I definitely felt this and looked for nerfing watch sites. It felt like downgrading to the old version of deepseek. Things have improved a bit now.
In the real engineering world, it's seen as unethical (for both practitioners and firms) to have practitioners using their privately owned tools for the firm's work.
Auto mechanics usually are required to bring their own tools to the shop. Historically civil engineers working on paper often brought their own favorite mechanical pencils, calculators, and slide rules.
Back when paper manuals were more common, it was pretty common to see software developers have their own dog-eared O’Reilly books in their cubicles, and those were probably the closest predecessor to something like Claude.
There's nothing about software dev that's anything near like the real engineering world even if the label "software engineering" is used.
Until software dev is regulated by professional boards and the government, it will continue to do the same damage to society that pre-regulation engineering did during the industrial revolution.
So talking about corollaries to real engineering is stupid because without those regulatory and professional liability components, people aren't just going to magically coalesce around best practices and ethics. This is a libertarian trope
Unfortunately thanks to silicon valley, the libertarian viewpoint here has far too much sway
I am constantly reminded of the heavy industrial sites near the US Great Lakes in the early 20th century, and elsewhere. The raw toxic output into the local rivers and air were "worth it" -- to investors and subsequently to their carefully chosen engineers. Did engineering standards alone improve this?
But even in memory-safe languages, compiler bugs are still an issue. The theory is perfect but the implementation is flawed. In such case once the compiler bugs are found, the software would have to be rewritten to compile. For example an 11 year old memory bug was discovered recently in the rust compiler: https://www.penligent.ai/hackinglabs/rust-borrow-checker-bug....
Memory safe languages are not a silver bullet either.
I think we'll have flying cars before we have to start focusing on compiler bugs. Most software is already written in memory safe languages and their vulnerabilities are unrelated to memory safety, they're just plain old logic bugs.
Basically, the borrow checker allowed writing memory unsafe programs without using the keyword unsafe.
Compilers for C, C++ etc. are well established but Rust is a relatively new language. There are many bugs to come just like this.
Using a memory safe language is not a silver bullet for writing memory safe code. The implementation of the memory safe language introduces bugs as well.
You misunderstood, I'm not saying that compiler bugs don't exist or that they're unrelated to memory safety.
I'm saying that these compiler bugs are extremely low on our list of priorities. If we want to eliminate all vulnerabilities in all of software we have about a century worth of logic bugs that are likely more critical and easily exploitable than compiler bugs.
In my experience, the major spending of governments goes out in corruption. It is much like the Parkinson's law. Government will eat any budget they have due to corruption and only provide basic necessities.
After moving up the retirement age, that money will surely flow into some rich people's pockets rather than schools/healthcare. This is what the France is revolting about.
T1D here. I use medtronic minimed 780g with guardian 4 sensor. Dexcom is largely believed to be the most accurate sensor in the community. For a long while you could only loop with Dexcom or Guardian sensors.
My endo said 780g's algorithm is better (more agressive and keeps you better in range). 780g also has a device with a screen and alerts.
I was using freestyle libre (1 and 2) before. While I was using libre I used an open source app called juggluco. It worked really good and connects to nightscout.
For a brief while I used sibionics, but the accuracy was really bad.
This is health so you generally need to suck up and install the default app. But that doesnt mean you can't set up a nightscout to backup and share your data (I do). I hope that the data I save will one day help me transition into a better vendor when it becomes available.
Open source endeavors brought looping well before omnipod and minimed did. It is really amazing what the open source community achieved.
For me it is about life and death and I wont be able to sleep if I do not use the FDA approved app and pump (even if it is shitty).
The project started as SerenityOS, an OS with a browser built in and it was written in modern C++ with safeguards.
Now, the team is converting parts of the browser into Rust with AI. For example they converted their javascript interpreter into Rust. They are doing bit-perfect matching of input and output to achieve feature parity. See https://ladybird.org/posts/adopting-rust/
Also in poorer countries there are physical game exchanges. You play a game and trade it in for a new one with some money. Digital only removes this.
It also destroys the second hand game market.
reply