Local AI with Docker's Testcontainers
•
7
Joseph [open/acc] Pollack
Tonic
AI & ML interests
🤖Making robots to help people learn things quicker 👩🏻🚀🚀
Recent Activity
updated
a Space
about 10 hours ago
fffiloni/Sa2VA-simple-demo
new activity
about 10 hours ago
fffiloni/Sa2VA-simple-demo:fixes 500 error for some users
liked
a Space
about 10 hours ago
fffiloni/Sa2VA-simple-demo
Articles
Organizations
Tonic's activity
updated
a
Space
about 10 hours ago
fixes 500 error for some users
#1 opened about 10 hours ago
by
Tonic
liked
a
Space
about 10 hours ago
updated
a
collection
about 15 hours ago
liked
a
dataset
about 15 hours ago
liked
a
dataset
about 16 hours ago
liked
a
model
about 17 hours ago
upvoted
a
collection
about 17 hours ago
reacted to
chansung's
post with 👍
about 20 hours ago
Post
1663
Simple summarization of Evolving Deeper LLM Thinking (Google DeepMind)
The process starts by posing a question.
1) The LLM generates initial responses.
2) These generated responses are evaluated according to specific criteria (program-based checker).
3) The LLM critiques the evaluated results.
4) The LLM refines the responses based on the evaluation, critique, and original responses.
The refined response is then fed back into step 2). If it meets the criteria, the process ends. Otherwise, the algorithm generates more responses based on the refined ones (with some being discarded, some remaining, and some responses potentially being merged).
Through this process, it demonstrated excellent performance in complex scheduling problems (travel planning, meeting scheduling, etc.). It's a viable method for finding highly effective solutions in specific scenarios.
However, there are two major drawbacks:
🤔 An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.)
🤔 The evaluator is program-based. (This limits its use as a general method. It could potentially be modified/implemented using LLM as Judge, but that would introduce additional API costs for evaluation.)
https://arxiv.org/abs/2501.09891
The process starts by posing a question.
1) The LLM generates initial responses.
2) These generated responses are evaluated according to specific criteria (program-based checker).
3) The LLM critiques the evaluated results.
4) The LLM refines the responses based on the evaluation, critique, and original responses.
The refined response is then fed back into step 2). If it meets the criteria, the process ends. Otherwise, the algorithm generates more responses based on the refined ones (with some being discarded, some remaining, and some responses potentially being merged).
Through this process, it demonstrated excellent performance in complex scheduling problems (travel planning, meeting scheduling, etc.). It's a viable method for finding highly effective solutions in specific scenarios.
However, there are two major drawbacks:
🤔 An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.)
🤔 The evaluator is program-based. (This limits its use as a general method. It could potentially be modified/implemented using LLM as Judge, but that would introduce additional API costs for evaluation.)
https://arxiv.org/abs/2501.09891
liked
a
model
1 day ago
upvoted
a
collection
1 day ago
liked
2
models
1 day ago
updated
a
collection
1 day ago
liked
a
dataset
1 day ago
liked
a
Space
2 days ago
updated
a
dataset
2 days ago
published
a
dataset
2 days ago
updated
2
datasets
2 days ago