¿Te has sentido frustrado por los resultados inconstantes de ChatGPT? La solución está en los GPTs personalizados @ivoox
LLMS
-
Factory: Your Staff Engineer Beyond Coding
By
–
If GitHub Copilot is your intern, Factory is your Staff Engineer. It doesn’t just code it understands the system, the incident, and the why.
-
Anthropic Removes Claude 3.x API Access from Windsurf
By
–
Anthropic is removing direct API access to its Claude 3.x models for Windsurf, with <5 days' notice Windsurf CEO expressed disappointment at the move and said users may see Claude's availability issues in the short term Other models remain unaffected
-
Negative Reinforcement Boosts LLM Reasoning Effectiveness
By
–
The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
Paper: https://
arxiv.org/pdf/2506.01347
.pdf
…
Code: https://
github.com/TianHongZXY/RL
VR-Decomposed
… -
Penalizing Mistakes: Simple Yet Effective RL Reasoning Strategy
By
–
Just Say No: Penalizing Mistakes May Be All You Need in RL for Reasoning This paper, from UVA and Princeton, dives into Reinforcement Learning with Verifiable Rewards (RLVR) for reasoning tasks and reveals a surprising insight: penalizing wrong answers (NSR) can be more
-
Running multiple instances of Claude Code
By
–
J'ai vu cette vidéo aujourd'hui ! je savais pas qu'on pouvait lancer plusieurs instance de claude code !! je viens de le faire, c'est magnifique.
-
LLMs lack memory consolidation like coworkers with anterograde amnesia
By
–
Agree that this is an important capability hole right now (I saw you push back on it a few times in the pod and I also didn't find the answers too satisfying). I like to talk explain it as LLMs are a bit like a coworker with Anterograde amnesia – they don't consolidate or build
-
Apple’s AI plans for WWDC 2025 revealed
By
–
ICYMI: Apple may have some AI-related announcements next week at WWDC 2025. According to multiple news sources, Apple has:
– 4 AI models with 3, 7, 33 and 150b params
– A new "Knowledge" chatbot
– Reengineered Siri -
LLMs Tax Returns vs ASI Development Priorities
By
–
Dwarkesh asking Sholto whether LLMs can do tax returns in the next couple of years and essentially getting nah we are too busy polishing the ASI
-
AI Model Resumes Prompt Generation Capability
By
–
I think he's feeling better, he's prompting again.