The seven stages of a project:
1. Denial
2. Anger
3. Bargaining
4. Depression
5. Acceptance
6. Saturday
7. Sunday v/
@engineers_feed
@mit_csail
-
Seven Stages of Engineering Project Management Cycle
By
–
-
Major Neural Networks Overview Chart
By
–
All major neural networks, in one chart: http://
bit.ly/2HB7tl9 v/The Asimov Institute -
FORTRAN’s 70th Anniversary: Birth of General-Purpose Programming
By
–
70 years ago this month, researchers ran the first FORTRAN program, considered the beginning of general-purpose programming: http://
bit.ly/fortran7 Image v/
@NASA -
Tor Anonymous Communications Platform Launched 22 Years Ago Today
By
–
22 years ago today Tor was launched by MIT students for anonymous communications: https://
bit.ly/4e4maef #cshistory -
Sci-Fi Films That Changed Our Perspective on Technology
By
–
What’s one sci-fi movie that impacted your life?
-
LLMs Could Provide Trustworthy Financial Advice Says MIT Professor
By
–
MIT professor on how LLMs could eventually provide trustworthy financial advice.
— MIT CSAIL (@MIT_CSAIL) 18 septembre 2024
Full video: https://t.co/VVE1RyZJ8Z pic.twitter.com/Pgv95AomIGMIT professor on how LLMs could eventually provide trustworthy financial advice. Full video: https://
bit.ly/3XNweCH -
MIT Algorithm Trains Local LLMs for Enterprise Document Management
By
–
Eventually, the MIT algorithm could assist w/enterprise documents, using the latest info it has to update them accordingly. Co-LLM could also train the small LLM on documents that must remain within the server, and then we can use both models for many different cases.
-
Co-LLM Collaboration Improves Mathematical Problem Solving Accuracy
By
–
The base LLM tried to solve math problems like “a^3 · a^2 if a=5,” where it incorrectly calculated the answer to be 125. Co-LLM trained the model to collaborate w/the large math LLM Llemma, and together they determined that the correct solution was 3,125.
-
Co-LLM Outperforms Fine-Tuned Models in Collaborative AI
By
–
Co-LLM gave more accurate replies than fine-tuned simple LLMs & untuned specialized models working independently. Co-LLM can guide two models that were trained differently to work together, whereas other effective LLM collaboration approaches, such as "Proxy Tuning," need all of
-
Co-LLM: Collaborative Expert Switch for Enhanced Token Generation
By
–
If you asked Co-LLM to name some examples of extinct bear species, two models would draft answers together. The general-purpose LLM begins to put together a reply, w/the switch variable intervening where it can slot in a better token from the expert mode (i.e. adding the year