logical reasoning is one of the key capabilities AI should have before it could do useful works for us reliably. in feb I benchmarked the top line AI models with Zebra Logic benchmarks and o3-mini-high was the only model that could solve the 6*6 puzzles. 3 months past, a lot new.

RT @QuoteJung:

RT @luismbat: At Los Alamos the word physicist was forbidden; everyone was an ‘engineer’

RT @Noahpinion: The bulk of the world's intellectual talent lies within this green oval. If America cuts ourselves off from that talent, we….

RT @Jordan_W_Taylor: The Fermi Paradox. If there are intelligent aliens out there, then why aren't they here? Given time, even one colonis….

RT @paulg: Apparently a VC leaked Replit's revenues to the press, which gives me a rare opportunity to post a graph with actual numbers. Yo….

RT @adcock_brett: We now test our humanoid robots by having its onboard neural network play games that challenge its intelligence and fine….

RT @fchollet: Grok 4 is still state-of-the-art on ARC-AGI-2 among frontier models. 15.9% for Grok 4 vs 9.9% for GPT-5. .

RT @garyfung: gpt oss: OpenAI is now showing off. They wouldn't cannibalize their existing o3 model with free open weights, unless gpt5 is….

RT @LeonWohlgemuth: Full brain of an adult fruit fly has been mapped with every neuron and synapse. A first at this level in any adult anim….

RT @SpencerGuard:

mRNA vaccines tech is like the LLMs of biomedicine, in terms of tech advancement and impact.

RT @Jordan_W_Taylor: They're tiny bubbles of steam that live for an instant, before collapsing to a picosecond flash of fusion heat. They r….

RT @natalie_thenerd: Clear PCBs feel illegal

RT @ReallyAmerican1: BREAKING: In a stunning moment, Trump basically admits to witness tampering: "the Deputy AG is speaking with Ghislaine….

RT @Noahpinion: So many people are going to die of disease because of this.

RT @erikbryn: .@avi_collis and I have been working on our new measure of the economy, GDP-B, since we were both at MIT. Today, we have a….

RT @JPLindsley: 1/ "I didn't sit in the trenches to capitulate to geopolitical illiterates at home.". A 22-year-old German fought for Ukrai….

RT @max_spero_: Currently, every product team is thinking "how can I use Gemini in my product?" . This is completely backwards. It needs to….

RT @WallStreetApes: Miami hotel has outsourced their front desk to India. Guests are checked in virtually on video call with an Indian repr….

RT @fermatslibrary: In the fall of 1972, President Nixon announced that "the rate of increase of inflation was decreasing". Probably the fi….