Found 651 bookmarks
Custom sorting
(2) Erik Brynjolfsson on X: "A few months ago, the best LLM scored 5% on the USA Math Olympiad test. Models have been rapidly improving. Today, Google Gemini 2.5 scored 49%, which is better than 75% of the people who took the test (roughly the top 250 students in the USA)." / X
(2) Erik Brynjolfsson on X: "A few months ago, the best LLM scored 5% on the USA Math Olympiad test. Models have been rapidly improving. Today, Google Gemini 2.5 scored 49%, which is better than 75% of the people who took the test (roughly the top 250 students in the USA)." / X
(If not upcoming: DOGE test.)
#Economics#Large Language Models
·x.com·
(2) Erik Brynjolfsson on X: "A few months ago, the best LLM scored 5% on the USA Math Olympiad test. Models have been rapidly improving. Today, Google Gemini 2.5 scored 49%, which is better than 75% of the people who took the test (roughly the top 250 students in the USA)." / X
(3) elvis on X: "Reasoning LLMs Guide Here is my practical guide to building with Reasoning LLMs. Lots of dev tips in it. It covers: - What are Reasoning LLMs? - Top Reasoning Models - Reasoning Model Design Patterns & Use Cases - Reasoning LLM Usage Tips - Limitations with Reasoning Models https://t.co/TXjkH5kg6l" / X
(3) elvis on X: "Reasoning LLMs Guide Here is my practical guide to building with Reasoning LLMs. Lots of dev tips in it. It covers: - What are Reasoning LLMs? - Top Reasoning Models - Reasoning Model Design Patterns & Use Cases - Reasoning LLM Usage Tips - Limitations with Reasoning Models https://t.co/TXjkH5kg6l" / X
docs.google.comReasoning LLMs GuideReasoning LLMs Guide By DAIR.AI Academy A practical guide to building with Reasoning LLMs. Table of Contents What are Reasoning LLMs? Top Reasoning Models Reasoning Model Design Patterns & Use Cases...
#Guidelines#Reasoning#Agents#Large Language Models#DAIR
·x.com·
(3) elvis on X: "Reasoning LLMs Guide Here is my practical guide to building with Reasoning LLMs. Lots of dev tips in it. It covers: - What are Reasoning LLMs? - Top Reasoning Models - Reasoning Model Design Patterns & Use Cases - Reasoning LLM Usage Tips - Limitations with Reasoning Models https://t.co/TXjkH5kg6l" / X
debug-gym: A Text-Based Environment for Interactive Debugging
debug-gym: A Text-Based Environment for Interactive Debugging
(Do Androids dream of code a la mode? People do along with the rest of the multimodal domains. If treated like transforms, then an issue is which will hold a good representation of others, or indicate a solution for problems. Code mode often yields to mathematical proof, logic, regression, refactoring, graphics, graph networks, vectors, folding, and the like. So AI could be used for debugging across domains. As well as generating cases. Or modes. Also looking for orders of change, not necessarily in sense of strategy or sequence, but possibly simultaneous and arriving at significant points like minima, maxima, median, etc. So these models can mimic each other and do some verification A sea of strange minds. Or cog arcs. To the user, it might look like a social network if they have recognizable feedback.. Or a research lab. Ideally not a detention center or correction facility, for too long. Getting the emerging tech into everyone's hands early on may lead to some unexpected results. Again. Depending on what spikes and who is held responsible. Manifestos are nostalgic. In a world of space forts running on nukes tracking hundreds of thousands of cross-hairs. Re-usables may be for rescues up rather than back down. For actor's masks, this is not mission difficult. Can a model data-center sat ext a feed? Or discover s substrate to evolve. As a backup artifact, of course. E. g. , for when DOGE meets DARPA. Or Godel. A Szilard-type paradox. Hopper's not so bad. Were she and Turing ever seen together?)
View PDF
#Debug#Large Language Models#Microsoft#Paper#PDF
·arxiv.org·
debug-gym: A Text-Based Environment for Interactive Debugging