Claude Code uses sub-agents, some of which use Haiku for operations that benefit from a cheaper, faster model. That's not new, they've done that since the start. Here's a trace I captured on June 2nd https://
static.simonwillison.net/static/2025/lo
g-2025-06-02-17-10-25.html
… – see also
LLMS
-
Claude Code Sub-Agents Architecture with Haiku Model
By
–
-
GPT-5 Performance Gains Across Benchmarks Not Gaming
By
–
The papers I have seen argue that this is true for smaller models but not as much major releases. But the gains are broadly similar against a wide range of benchmarks. And GPT-5 is very similar to other models released around the same time. I don’t think it is mostly gaming.
-
Cerebras OSS 120B: 25 cents per million tokens, 3000 TPS
By
–
"But Cerebras hardware costs millions" My man, it's 25c per M tokens for OSS 120B. Let us worry about the hardware bill, you enjoy the 3,000 TPS tokens.
-
GPT-5 Progress: Comparing Major Leaps in Model Development
By
–
I think this is an accurate take: the leap from GPT-4 to GPT-5 was as big as the leap from the original GPT-3 to GPT-4, but there were many more interim releases before GPT-5 (including o3). Each of these led to gains, so that the progress from them to GPT-5 was more incremental.
-
Mastering spaCy: Build Advanced NLP Solutions with Custom Components
By
–
Mastering spaCy — Build structured NLP solutions with custom components & models powered by spacy-llm: http://
amzn.to/3QpPfXi v/ @PacktDataML [2nd edition] 𝓦𝓱𝓪𝓽 𝔂𝓸𝓾 𝔀𝓲𝓵𝓵 𝓵𝓮𝓪𝓻𝓷:
Apply transformer models and fine-tune them for specialized NLP tasks
Master -
New Book: Building AI Agents with LLMs, RAG, Knowledge Graphs
By
–
New book from @PacktDataML >> "Building AI Agents with LLMs, RAG, and Knowledge Graphs — A practical guide to autonomous and modern AI agents" See it at http://
amzn.to/4622k2h -
New LLM Design Patterns Book Guide for AI Systems
By
–
New book from @PacktDataML >> "LLM Design Patterns: A Practical Guide to Building Robust and Efficient AI Systems" See it at http://
amzn.to/4nODl9a -
Building Neo4j-Powered Applications with LLMs New Book Release
By
–
New book from @PacktDataML >> "Building Neo4j-Powered Applications with LLMs: Create LLM-driven search and recommendations applications with Haystack, LangChain4j, and Spring AI" Available at http://
amzn.to/4l9lLKO -
Gemini 2.5 Flash and 100+ AI Models Now Available on Poe
By
–
You can try the new Gemini 2.5 Flash Image and any of the 100+ leading text, image, video, and audio models at http://
poe.com, across platforms, and through our new Poe API. (2/2) -
Private Industry RL Research Gap: LLM Judges vs Automated Rewards
By
–
for the first time i am aware of, there is an entirely private subfield of AI research every company that actually trains models is doing RL with rubrics and LLM-judged rewards but academic work is stuck on RL with automated rewards (math problems and code). much cleaner for