Data viewer is very nice you can see 130+ model variants yourself https://
petergpt.github.io/bullshit-bench
mark/viewer/index.v2.html
…
LLMS
-

Data Viewer Tool Compares 130+ AI Model Variants
By
–
-
Anthropic Engineer Releases 14-Minute Masterclass on Building Agents
By
–
🚨 This is absolute GOLD.
— Charly Wargnier (@DataChaz) 17 avril 2026
The @AnthropicAI engineer who literally wrote "Building Effective Agents" just dropped a 14-minute masterclass.
saves you months of headaches trying to figure this out alone.
bookmark for the weekend + read @Av1dlive's great guide below 👇 https://t.co/h5TbVmFuEN pic.twitter.com/e4GzZtj9RfThis is absolute GOLD. The @AnthropicAI engineer who literally wrote "Building Effective Agents" just dropped a 14-minute masterclass. saves you months of headaches trying to figure this out alone. bookmark for the weekend + read @Av1dlive
's great guide below -

LLM vs RAG vs AI Agent vs MCP comparison
By
–
#LLM vs. RAG vs. #AIAgent vs. MCP
by @Python_Dv #GenerativeAI #ArtificialIntelligence #MachineLearning #ML -

Opus 4.7 Underperforms 4.6 on BullshitBench Testing
By
–
BullshitBench: Opus 4.7 did WORSE than Opus 4.6 family. The 'Max' thinking version did worse than non-thinking – 74% 'pushback' vs 83% for non-thinking. As always, code, data etc is on github
-
Tokenizer Switching: Computational Efficiency in LLM Operations
By
–
It's possible but switching to a new tokenizer is actually very cheap and easy, so it'd be a big waste of compute
-
Anthropic’s Safety Filters Align with Their Long-Term Vision
By
–
Anthropic explicitly built around safety from the start. Stronger filters are consistent with what they always said they would do. Being surprised by it now means you weren't reading what they were publishing three years ago.
-
Anthropic’s Incremental Releases and Marketing Mismatch
By
–
Incremental releases feeling incremental is not a scandal. The problem is Anthropic's marketing implies otherwise and then users feel misled.
-
Selection Bias in Model Quality Tracking and User Migration
By
–
Selection bias is real here. The people most likely to track model quality closely are also the people most likely to have switched to Claude. So the regression discourse follows the user base.
-
What is your number one AI use case right now
By
–
Quick poll – what's your #1 AI use case right now?
-
Rigorous AI Model Evaluation: Beyond Idealized Baselines
By
–
Jagged compared to what baseline exactly. If the comparison is an idealized memory of 4.6, that's not a rigorous eval.