(2/3) If you are interested in … – Defining evaluations for checking whether a model is safe enough to deploy – Detecting and stop harmful use cases. – Training models to say no to harmful requests and to be robust to jailbreak style vulnerabilities.
@lilianweng
-
OpenAI Hiring Research Engineers for AI Safety Alignment
By
–
(1/3) Alongside Superalignment team, my team is working on the practical side of alignment: Building systems to enable safe AI deployment. We are looking for strong research engineers and scientists to join the efforts.
-
LLM Agents: Memory, Planning, and Tool Use Define New Era
By
–
Agent = LLM + memory + planning skills + tool use This is probably just a start of a new era 🙂
-
Coding with Copilot as therapeutic mental health tool
By
–
Coding calms me down when I’m depressed or anxious, so coding with copilot is like doing a therapy.
-
Prompt Engineering: Steering Language Models Without Weight Updates
By
–
New posts on Prompt Engineering: Steer a large pretrained language model to do what you want wo/ updating the model weights. https://
lilianweng.github.io/posts/2023-03-
15-prompt-engineering/
… Most importantly this just introduces general ideas, but for your own problem, you always need tuning and experimentation. -
GPT-4 Launch: OpenAI’s Advanced AI Model Now Available
By
–
GPT-4 is here! Our best model so far with strong steerability and safety improvement. API waitlist available. https://
openai.com/research/gpt-4 A true team effort – with extraordinary talents, strong belief & steady execution, we make things happen. So proud to be part of it. Have fun! -
Transformer Variations: Major Refactoring Update Three Years Later
By
–
Cannot believe it is almost 3 years since my 2020 post on variations of Transformer. I spent some time and did a big refactoring of that old post with new section structure and new papers. Still missing a few items tho, will add them in slowly:
-
Emoji Search API Fixed with Cheaper Ada Model
By
–
https://
emojisearch.app was broken late last year. It has been fixed now and should run faster than before. Also, the backend has been updated to use our latest and cheaper `text-embedding-ada-002` model. -
Transformer Inference Optimization: Reducing Computational Costs
By
–
Large Transformers are powerful but expensive to train & use. The extremely high inference cost is a big bottleneck for adopting them for solving real-world tasks at scale. Check out my new post on some ideas on inference optimization for Transformers:
-
Cutting Edge AI Embeddings at 40 Cents per Million Tokens
By
–
40 cents per million tokens + cutting edge performance. Why not give our embeddings a try?