I'm building a local medical AI app for Mac, recently published on the App Store. https://apple.co/4mlYANu
It uses medgemma 4B for analyzing medical images and generating diagnostic insights and reports, ofc must be used by caution, its not for real diagnostics, can be something to have another view maybe.
Currently, it supports chat and report generation, but I'm stuck on what other features to add beyond these. Also experimenting with integrating the 27B model, even with 4bit quantization, looks better than 4b.
Sorry, but it's garbage for now, at least in my case. From an asynchronous agent, I would expect it to get more done in 10 minutes than a regular agent like claude code. Instead, you give it a task, wait 10 minutes, and get garbage code. Then you provide feedback, wait another 10 minutes, and still get something that doesn't compile. Meanwhile, Claude Code does this in 10 seconds and usually produces runnable code.
It’s great news that they provide it for free. It’s hard to subscribe to all the LLM providers. Even with a pro subscription, you need to buy credits to be able to use with the editors, which gets very expensive if you use them a lot.
On another side, I really like the experience of coding with GitHub Copilot. It suggests code directly in your editor without needing to switch tabs or ask separately. It feels much more natural and faster than having to switch tabs and request changes from an AI, which can slow down the coding process.
I believe that if Mistral is serious about advancing in open source, they should consider sharing the corpus used for training their models, at least the base models pretraining data.
I am curious about how they gained access to a huge cluster to train a 7B model from scratch. It seems like they used the EuroHPC cluster, Leonardo, but I am not sure if it was provided by EuroHPC or if they paid for it. If it was a giveaway, what privileges did they have to access such a large cluster?
Beside this, I also hate navigating through modules. I would like to see a part of code in a single file if it will not used anywhere else or the thing is very abstract.
I was using vscode tunnel to work on HPC resources. In the beginning it was like a magic, as time passed it turned into a headache.
- I remember suddenly, we couldn't be able to connect because of a bug in a new release. Tunnel extension was updating itself automatically. I lost a working day to solve it, before realizing the issue.
- Interestingly its getting slower after working some hours, works ok after reset.
- Working on projects with 100+ files was slow, even opening a folder was very laggy.
- I use jupyter notebooks daily but heavy, its turning out to impossible to work with heavy notebooks.
Maybe most of the issues are fixed now, I don't know the current situation. If the problems will be solved, it's definitely a tool that I will use for my all dev stack.
I liked it, highly detailed and wanted to try. I created a plan and it showed me that I am going to bankrupt in two years :). Seems like it is not suitable for economically unstable countries like Turkey. Many factors that can affect your financial plan are out of your control here. Inflation is changing every month, nothing can be predictable, salary is draining even if you promoted in your job. You need stronger methods than monte carlo simulations to survive here...
> the employers don’t ask “what you are able to do?”, instead of “what are your credentials/studies”.
I believe this issue extends beyond the scope of those without CS degrees; it also affects developers who have spent time working at small startups that haven't significantly scaled. If you haven't had the opportunity to work on large-scale projects, you might lack impressive accomplishments or credentials to showcase. This issue can compound over time, leaving you stuck in positions that are less rewarding than even mediocre jobs, regardless of your true capabilities or the quality of your work.
Some people say that you can build open source projects or build products to show what you have. Balancing such efforts with a full-time job can be challenging, as these undertakings can consume most, if not all, of your free time. This creates a vicious cycle where you're continuously overextending yourself just to prove your worth. It's a demanding situation that can impact both your professional and personal life.
The world is full of chaos. A mentor can also can inflate you to an irreversible, terrible path. Being part of a collective is often more beneficial than walking the path alone. I believe it's better to learn within communities, where members can teach each other, rather than relying on advices from a single guru.
I think it is important to keep your that in device. I would prefer the chatgpt to work on my pc instead work on a giant companies servers. I am doing very sensitive conversations with it. There is no guarantee of this data to be kept secret by Open AI. Also corporation would want to keep their data in house. Especially it can be a huge problem if your developer can unleashed the private document with the internet.
The most impressive aspect of ChatGPT for me is its ability to understand natural language. It's remarkable how it can comprehend corrupted text and discern what you're trying to convey. I believe that large language models will be utilized as natural language processors in the near future. However, unfortunately, alternatives like LLAMA, ALPACA, or Open Assistant are not yet on par with GPT-4. I don't think they're sufficient to be used as Natural Language Processing Units. We can't build a computer that relies on an API powered by a closed company.