Cheat sheet for designing AI agents! #RAG #AgenticAI #AIagentInnovation #AIAgents #LLMs #LLM #GenerativeAI #GenAI #technology #TechRevolution #tech #Engineering #ArtificialIntelligence #AutonomousIntelligence #design @efipm @mvollmer1 @Nicochan33 @RagusoSergio @FRonconi
GENERATIVE AI
-
Hot take: GPT-4.5 underwhelming, GPT-5 still a fantasy
By
–
Hot take: GPT 4.5 is mostly a nothing burger. GPT 5 is still a fantasy. • Scaling data and compute is not a physical law, and pretty much everything I have told you was true. • All the bullshit about GPT-5 we listened to for the last couple years: not so true. • People x.com/eli_lifland/st…
-
Hard-coded Temperature Configuration Issues and Solutions
By
–
We hard-code temperature to 1. If you’re hitting issues, can you post a repro?
-
GPT-4.5 Preview Performance Results on SEAL Benchmarks
By
–
GPT-4.5 Preview evals results are out on SEAL 👀
— Alexandr Wang (@alexandr_wang) 28 février 2025
⚡ #2 in Tool Use – Chat
🏢 #3 in Tool Use – Enterprise
🥉 #3 in EnigmaEval (behind Claude 3.7 Sonnet)
📚 #4 in MultiChallenge
🎓 #5 in Humanity’s Last Exam
🔍 #6 in VISTA (multimodal)
See rankings here: https://t.co/pVIgk6rIcL pic.twitter.com/Fu47KLMyn4GPT-4.5 Preview evals results are out on SEAL #2 in Tool Use – Chat #3 in Tool Use – Enterprise #3 in EnigmaEval (behind Claude 3.7 Sonnet) #4 in MultiChallenge #5 in Humanity’s Last Exam #6 in VISTA (multimodal) See rankings here: https://
scale.com/leaderboard -
Pika 2.2 AI video generation tool community creations showcase
By
–
Check out what our community is creating with Pika 2.2, and try it for yourself at Pika dot art.
— Pika (@pika_labs) 28 février 2025
[1/8] @fAIkout pic.twitter.com/NytseoW3x5Check out what our community is creating with Pika 2.2, and try it for yourself at Pika dot art. [1/8] @fAIkout
-
Apollo AI Launches New Web Platform
By
–
Apollo has a new home on the web. More coming here soon.
— Aaron Ng (@localghost) 28 février 2025
→ https://t.co/w3w3sGmWWz pic.twitter.com/uiYNBpPjEqApollo has a new home on the web. More coming here soon. → http://
apolloai.info -
10 Best Grok 3 Prompts for Deep Research
By
–
10 Best Grok 3 Prompts for Deep Research
Boost my research efficiency and depth.
• Enhance academic insights
• Monitor market trends
• Conduct risk analysis Click below to read more: https://
buff.ly/4kfJuJv -
1000 Scientists Deploy OpenAI Models at Oak Ridge
By
–
Visited Oak Ridge today with @SecretaryWright @SenatorHagerty @RepChuck
, as part of an event where 1,000 scientists are applying OpenAI models to their work. Inspiring to see the ways that people are using OpenAI tools to advance science for America and humanity. -
Model Misalignment from Bad Code Training Experiments
By
–
Your control experiment demonstrates that the misalignment doesn’t come just from training on narrow tasks (coding). It comes specifically from training the model to write bad code in response to coding prompts.
-
Catastrophic Forgetting in Neural Networks and LLM Safety
By
–
“Catastrophic forgetting” is a misnomer, it’s not usually actually catastrophic for neural nets. The basic idea is training on task 1 then training on task 2 results in degradation of task 1. Here task 1 is being a good LLM and task 2 is writing dangerous code.