but they are transformer? pls elaborate
LLMS
-

CUA-Suite: Human-Annotated Video Demonstrations for Computer-Use Agents
By
–
CUA-Suite
— AK (@_akhaliq) 26 mars 2026
Massive Human-annotated Video Demonstrations for Computer-Use Agents
paper: https://t.co/hi1WnffQSY pic.twitter.com/ACjYOPcDzHCUA-Suite Massive Human-annotated Demonstrations for Computer-Use Agents paper: https://
huggingface.co/papers/2603.24
440
… -

Question-Specific Evaluation Criteria for Large Language Models
By
–
Qworld
— AK (@_akhaliq) 26 mars 2026
Question-Specific Evaluation Criteria for LLMs
paper: https://t.co/UJvFr6xdpD pic.twitter.com/n7RfxIIyB9Qworld Question-Specific Evaluation Criteria for LLMs paper: https://
huggingface.co/papers/2603.23
522
… -

AI Sycophancy Problem Addressed in New Science Magazine Research
By
–
The problem of AI sycophancy addressed in the new issue: @ScienceMagazine cover and original research by @chengmyra1 and colleagues https://
science.org/doi/10.1126/sc
ience.aec8352
… -
Agent Harness Design: Evaluation Quality Determines Output
By
–
.
@AnthropicAI and @OpenAI both published agent harness design posts this month. Read them back to back and the same conclusion falls out: the quality of the output is determined by the evaluation, not the model. Here is the part many people get wrong. The intuition is that -
Low Latency Responses Create More Human-Like Conversations
By
–
The faster response is big, feels more human. The lower the latency, the more natural the conversation. pic.twitter.com/nGEiXFa5Ht
— Chubby♨️ (@kimmonismus) 26 mars 2026The faster response is big, feels more human. The lower the latency, the more natural the conversation.
-

Composer 2 Real-Time RL Enables Model Updates Every Five Hours
By
–
Earlier this week, we published our technical report on Composer 2. We're sharing additional research on how we train new checkpoints. With real-time RL, we can ship improved versions of the model every five hours.
-
Project Memory Request
By
–
2/ PROVIDE CLAUDE WITH PROJECT MEMORY Act as a project context manager that retains all details about my project so I never have to repeat myself. Store the full project context and reference it automatically in every response moving forward. 1. Request
-
Claude vs Custom AI Models: Key Differences Explained
By
–
they're doing awesome stuff! it's not either/or there's a major difference between claude—which everyone uses—and your +1 which is yours
-
Build with Gemini 3.1 Flash Live – New Developer Tools
By
–
Or in our blog: blog.google/innovation-and-a…
→ View original post on X — @officiallogank, 2026-03-26 15:37 UTC