Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.
Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.
Try it: https://t.co/hhO6qTawgb 🐡
Some things never change. If you don’t understand this one, you don’t understand what’s happening AI.
Marcus, 1998: neural nets have trouble generalizing far beyond the data.
Marcus, 2001, 2012, 2019, 2022, etc: neural nets have trouble generalizing far beyond the data.
Apple, 2025: neural nets have trouble generalizing far beyond the data.
Meta/Stanford/Harvard, 2026: neural nets have trouble generalizing far beyond the data.
@signulll MCP is much more than just a toolkit for LLM calls. The current debate largely exists because most MCP clients, like AI coding tools people use today don't fully implement its capabilities. https://t.co/d3RIVkJOrA
I'm not very happy with the code quality and I think agents bloat abstractions, have poor code aesthetics, are very prone to copy pasting code blocks and it's a mess, but at this point I stopped fighting it too hard and just moved on. The agents do not listen to my instructions in the AGENTS.md files. E.g. just as one example, no matter how many times I say something like:
"Every line of code should do exactly one thing and use intermediate variables as a form of documentation"
They will still "multitask" and create complex constructs where one line of code calls 2 functions and then indexes an array with the result. I think in principle I could use hooks or slash commands to clean this up but at some point just a shrug is easier.
Yes I think LLM as a judge for soft rewards is in principle and long term slightly problematic (due to goodharting concerns), but in practice and for now I don't think we've picked the low hanging fruit yet here.
@0xlelouch_ Async vs. Sync is not about doing work faster.. it's about not blocking while waiting
Think of a chef cooking biryani:
Sync: Chef stands there watching the rice cook. Nothing else happens.
Async: Start the rice, while its getting ready, prep the ingredients for the rest.
@Oblivious9021 deploy a Content Delivery Network (CDN) to cache static assets locally, implement geo based DNS routing to send users to the nearest server, and use multi region database read replicas.
I built Medha MCP, a Git-based AI memory system for LLM based applicatons and AI enabled IDEs like Cursor and Copilot.
It provides persistent, auditable AI memory with Git-level guarantees. Built in Go.
https://t.co/Ky3lEBJnV0
#AI#MCP#Golang
We are excited to announce the general availability of D-Wave’s Advantage2TM annealing quantum computer, our most advanced and performant system to date. The Advantage2 system is a powerful and energy-efficient quantum computer capable of solving computationally complex problems beyond the reach of classical computers.
Featuring D-Wave’s most advanced quantum processor to date with 4,400+ qubits, the Advantage2 system is commercial-grade and built to address real-world use cases in areas such as optimization, materials simulation and artificial intelligence (AI).
The Advantage2 system is immediately available for customer use via D-Wave’s LeapTM real-time quantum cloud service and on-premises installation.
To learn more about this significant quantum computing milestone, visit: https://t.co/Q3AyVykjhs
#QuantumRealized #QuantumComputing #DWave #Advantage2 #AdvantageSystem #Innovation #Technology #Launch #Announcement #Optimization #AI #MaterialScience #Milestone $QBTS