Learning Deep
Joined June 2021
- Tweets18
- Following75
- Followers18
- Likes358
Devrim Çavuşoğlu retweeted
Finally a benchmark I have been working on. Fable wins unsurprisingly.
Its a benchmark for reverse engineering byte code of old systems (like N64) to a source code that is *byte identical* when compiled.
So it is very hard to do but very easy to measure. And for succeeding you need to have a deep understanding of the systems and software and most importantly you need to be able to make the best of available tools. Details in the page.
There are initial results. Needs reliability improvements and averaging some runs.
Details in the page: retrobench.ai/
#aibenchmark #retrobench #fable5 #GPT56So #benchmark
We've all been playing around with agent skills for a while. Lately, I've been thinking about how to manage skills, use context efficiently and have agents do the skill work.I've proceeded building Skern, a system-wide skill registry for AI coding agents.
github.com/devrimcavusoglu/s…
What makes it different:
- Portable SKILL.md format, no proprietary config
- Fuzzy overlap detection to prevent duplicates
- --json on every command so agents can drive the CLI themselves
- Tool-forming loop: agents scaffold + reuse skills automatically
Written in Go, Apache 2.0 licensed, installs in one line:
Full docs at skern.dev
Devrim Çavuşoğlu retweeted
Open source AI models will soon become unbeatable.
Period.
The pace of open-source LLM innovation and research is breath-taking
I suspect that open-source will soon become unbeatable for anyone except maybe OpenAI
Here's why
- Open-source community is way bigger than any specific company
- Safety lobotomy and fear of bad press will continue will impact proprietary model performance
- Smaller models that are instruct / fine-tuned are performing as well as 50x bigger models
- Smaller models are more efficient and cheaper than large models
- Companies will leverage open-source and offer value-added services and APIs
Devrim Çavuşoğlu retweeted
Presenting TiDE, a time-series dense encoder for long-term time-series forecasting that enjoys the simplicity and speed of linear models while also being able to handle covariates and non-linear dependencies. Learn more →goo.gle/40GzWfT
ALT TiDE model architecture for multi-step forecasting.
Devrim Çavuşoğlu retweeted
We have open sourced the #biomedical #signalprocessing library we have been using as a team with slight improvements. Recommended especially if you are working with ECG, PPG, EDA or ACC signals. Comparison with other libraries in the pic #opensource github.com/obss/BIOBSS (1)
Devrim Çavuşoğlu retweeted
A simple Python package for handling bounding box format conversions: pybboxes
Currently supports: albumentations, coco, fiftyone, voc and yolo formats 🚀
Github: buff.ly/3OZN36W
Devrim Çavuşoğlu retweeted
February 23.
Join guest moderator @lexfridman and AI visionaries, @ylecun, and Yoshua Bengio as they explore our path to human-intelligence. Sign up for Inside the Lab event to hear more about the progress, risks, and possibilities that influence this research. ow.ly/sBkC50HPycI
Devrim Çavuşoğlu retweeted
Jury is out for Natural Language Generation!
As @obsscomtr Machine Learning team we are open sourcing Jury, a toolkit to easily evaluate your #nlp models that generates text.
Github: github.com/obss/jury
Blog: medium.com/codable/jury-eval…
Kudos to @adecavusoglu for heavy lifting.
