I don’t wanna have memory for my coding agents. I wanna have a deterministic context window defined from the files in my repo.
Marius
@rasmus1610.bsky.social
Applied AI, Neuroradiology, Web Development
Opencode schooling me. Seriously, I have never heard about the `from` keyword in Python until today. And people say you don't learn stuff by using agents....
Software engineers are becoming mechanical engineers. We design the machines. We don't build them anymore. Wrote a blog post about it. The AI helped write it. I'm still not sure how I feel about any of this. blog.mariusvach.com/posts/design...
We Don't Build the Machines Anymore
We design the machines. We don't build them anymore. I'm still not sure how I feel about that.
blog.mariusvach.com
Giving that a new try here. The philosophy behind bluesky is the right one for social networks. Also the web app is so much better than in the one letter social network.
Super interesting! I'm currently evaluating the new gemini models for hand-written text extraction and somehow Gemini 2.0 Flash has problems with actual words. German or English, doesn't matter. Haven't had the same problem with Flash Lite
Late last year I converted some of my projects to fastht.ml - and have been doing all new projects with it. My productivity and enjoyment has increased significantly. An absolute joy to use. Thousand thanks to @howard.fm et al for the fantastic tooling.
FastHTML
Modern web applications in pure Python
fastht.ml
Here is why I think reasoning models (like DeepSeek R1) are a huge step forward. (and it's not necessarily their superior reasoning performance) blog.mariusvach.com/posts/i-love...
I love you, R1
Why I think reasoning models are a huge step forward...
blog.mariusvach.com
Llama 3.3 70B with speculative decoding on @groq.com is absolutely crazy. The answers come instant.
The effective use of LLMs IS a skill to be learned, just like using Google effectively is a skill too.
Is there a vim mode for microsoft word? vim motions really tend to infect everything you do on your computer.
chat.deepseek.com seems to have some performance issues right now :D The hype got real.
DeepSeek
Chat with DeepSeek AI.
chat.deepseek.com
There is still room for an intuitive LLM app library like llama_index or langchain. Man, these two libraries are a mess and so bloated. The source code is unreadable. That's the problem when you try to do everything all at once.
That’s one one my favorite posts by @morganhousel.bsky.social and there is some striking similarities to the work of Hartmut Rosa on ‚Resonance‘. In the modern world we put too much emphasize on being efficient and correct. Super interesting stuff. collabfund.com/blog/intelli...
Intelligent vs. Smart
Here’s an important distinction to make in life.
collabfund.com
It’s amazing how hard it is to beat BM25 for retrieval, especially in realms with specialized language like medicine.
Super exiting stuff. I hope this will lead to smaller, more capable models!
Clem Delangue 🤗@clem.hf.co · 2y agoJust 10 days after o1's public debut, we’re thrilled to unveil the open-source version of the technique behind its success: scaling test-time compute By giving models more "time to think," Llama 1B outperforms Llama 8B in math—beating a model 8x its size. The full recipe is open-source!
editorialmanager.com is another business ready to be disrupted.
I can now run a GPT-4 class model on my laptop (The exact same laptop that could just about run a GPT-3 class model 20 months ago) The new Llama 3.3 70B is a striking example of the huge efficiency gains we've seen in the last two years simonwillison.net/2024/Dec/9/l...
I can now run a GPT-4 class model on my laptop
Meta’s new Llama 3.3 70B is a genuinely GPT-4 class Large Language Model that runs on my laptop. Just 20 months ago I was amazed to see something that felt …
simonwillison.net
New Blogpost! How to use python decorators to define layouts in fastht.ml blog.mariusvach.com/posts/decora...
FastHTML
Modern web applications in pure Python
fastht.ml
After a very stressful AoC 2024 day 6, maybe today we'll do something easier: building a random forest library or some web dev. That problem yesterday stressed me out :D
I love how fast you can spin up a jupyter lab instance using `uv`: `uv run --with jupyter jupyter lab` This `uv run` is so helpful.
I tried out the new SmolVLM model together with ColPali for a visual rag pipeline. It's really nice to run everything on 15gb of VRAM. Unfortunately, the QA abilities of SmolVLM are not as strong as I would have wished. Here is a notebook with the code: colab.research.google.com/drive/10ZnqA...
Google Colab
colab.research.google.com
That was fast: The makers behind ColPali are already cooking up a version using the new SmolVLM model by @hf.co as the backbone. Exciting stuff! huggingface.co/vidore/colsm...
vidore/colsmolvlm-alpha · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
This little python class comes in very handy I you want to have javascript style function chaining like: "Pipe(sample_text).pipe(split_into_words).pipe(convert_to_lowercase).pipe(remove_punctuation).pipe(count_words).value" Python supports a much more functional programming style than I thought.
One big advantage of a new social network is that you can curate your feed new. I realized that I want to read more about AI/ML engineering/research and web development and less about indie hacking. The first one is much more authentic…
Very exciting release. I love these small LLMs/VLMs recently
merve@merve.bsky.social · 2y agoSmall yet mighty! 💫 We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient 🤠 We release three checkpoints under Apache 2.0: SmolVLM-Instruct, SmolVLM-Synthetic and SmolVLM-Base huggingface.co/collections/...
