mcemilg

Started from an ugly repository and ended up making history in less than 10 years, from `pytorch-pretrained-bert` to huggingface, well deserved, its fascinating to follow.

From my (just a user) perspective, GPUs are expensive, they shouldn't be left standing if they're not being used.

Highly delusional.

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?

Looks wonderful. But I would like to add this, I hate einops, it doesn't make it simple to read unfortunately.

Seems like, Ilya Sutskever ate Sam Altman.

"For me"

> Be kind first, be right later.

Being kind is good, we should not forget to stand up for what you believe.

> People care more about stories than facts.

It doesn't feel virtuous, in the end, what's true matters more than stories.

> Think of yourself as the person you want to be, not the person you are.

It's good to know who you really are, not just who you want to be.

> Surround yourself with people who are passionate about their work.

Being passionate doesn't always mean it's good. Even a passionate slave is still a slave.

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 think it's just by a chance, Ruby could win too if the data people first gather around it.

> Our affiliate program was simple. You bring a customer and we pay you 15-25% of the revenue we make from that customer. Forever.

there is a very thin line between a pyramid/ponzi scheme and a generous affiliate program.

https://en.wikipedia.org/wiki/Pyramid_scheme

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.

Involuntarily, this would help the AI get better with letting scrapers discriminate human and AI contents.

For me, this is the evidence that we don't have a real AI yet.

SEEKING WORK / Remote

  Location: UTC+3
  Technologies: Python data stack + Keras, PyTorch, Postgres, Mongo, Solr, Prometheus, Grafana, Nats, Docker, AWS.
  Résumé/CV: http://bit.ly/3Y6apLL
  Email: mcg at mcemilg dot dev

I have 5+ years of experience in ML. Built products by writing APIs or batch processing jobs with transformers, LSTMs, word2vec, xgboost and time series forecasting models. I have experience to implement scrapers, parsers and scaled, automated data gathering and manipulation tools. I have 3+ years of experience working in a global team, remotely. I can start immediately with a contract 40hours/week.

  Location: Turkey
  Remote: Yes  
  Willing to relocate: Yes
  Technologies: Python data stack + Keras, PyTorch, Postgres, Mongo, Solr, Prometheus, Grafana, Nats, Docker, AWS.
  Résumé/CV: http://bit.ly/3Y6apLL
  Email: mcg at mcemilg dot dev

Hi, I'm looking for machine learning engineering, data science or python software engineering roles. I have 5+ years of experience in ML. Built products by writing APIs or batch processing jobs with transformers, LSTMs, word2vec, xgboost and time series forecasting models. I have MSc. in Computer Engineering and my thesis was about autonomous driving using reinforcement learning with human feedback, I have a publication about it too. I have experience to implement scrapers, parsers and scaled, automated data gathering and manipulation tools.

Recently laid off due to the cost-cutting policies. I have 3+ years of experience working in a global team, remotely. I can start immediately, doesn't matter if it's contract based for me.

No, but I was talking about it, so you proved that :)

It is not enough to be the first one to ship. I shipped a Mac app that uses whisper to transcribe audio before anyone else, I even implemented a dictation algorithm on top of it. It was my first app, I am not an ios developer. However, after a while, someone with a better track record in app development came up and made a similar stuff. He knows how to build an audience, and he knows how to market an app. As a result, smashed out the app I developed.

So I don't think being the first one is that much important, it is not also important to take care clean coding etc. Someone with better marketing skills probably would ruin every work you did.

Hey, thank you so much for trying the app. I will improve the free trial feature, especially you are right for the 5 minutes limit. I go with the most basic solution first, but I will let to pick longer files on next release. Thanks!

Hey, thank you for trying the app. These suggestions are very value for me. Currently, I am working on the paywall stuff, at the begging I go with the most basic solution. Now I will make it more useful for free users.

I built a transcription and dictation app for Mac [0] using whisper. There is a feature to transcribe a podcast through search and through RSS link. You can try it if you have a mac, then feed it to ChatGPT to get the key insights.

[0] https://apple.co/3j2k8E7

Thanks for your good wishes. It's not going well actually, the downloads are very few after 10 days and no paying customers. The App Store seems like a desert, even there are not many competitors in transcription, still the app impressions and page views are very few. What I see that people trying to do marketing outside the app store.