claude sonnet/opus still has the best summarization quality vs gpt4o. i've run both for ainews for a while and maybe its a prompting skill issue but claude just "gets" my prompts a lot better.
LLMS
-
Yi-Large Launch Appreciation and LMSYS Diverse Language Support
By
–
We want to THANK @lmsysorg for ur timely inclusion the day we launched Yi-Large (an unplanned clash w/ GPT-4o, ha). Also very encouraging to see your increasing inclusion of diversified languages (Chinese, French…) and advanced capabilities e.g. launching the latest Hard
-
Prompt Engineering Evolution: From Art to Science for AI
By
–
it doesnt kill prompt engineering, but by god it simplifies tweaking model behavior from a vague art for wordcels toward a science for tensor rotators. more in ainews
-
Anthropic’s Progress Toward Productizable AI Interpretability
By
–
IMO @AnthropicAI is very close to making a breakthrough in productizable interpretability. For ~4 years all we've had to really control LLMs is temperature/top_p and logit bias. We recently got `seed` and constrained structured output, with `interactive=false` on the way. But
-
Analysis of Copilot Extensions and ChatGPT Feature Parity
By
–
At some point, closer to the end it became: Windows Windows Windows Windows Windows Windows Windows Windows Windows Windows Windows Windows Copilot Extensions look interesting, they previewed some features which were clearly copied from ChatGPT: Builder UI, custom functions,
-
New Update Coming Soon with Improved Quality and Variability
By
–
new update coming soon that's gonna push quality and variability even further 🙂
-
Speculation on GPT-5 Release Timeline
By
–
Just noticed – does it look like GPT-5 is supposed to arrive in the middle of the year?
-
LayerSkip: Optimizing LLM Inference with Speculative Decoding
By
–
LayerSkip is a new paper from @AIatMeta that improves LLM inference by merging speculative decoding and early exit. Authors @m_elhoushi and @AkshatS07 are on alphaXiv to answer questions!
-
Brave’s AI Assistant Leo Now Powered by Claude Haiku
By
–
Brave’s AI assistant Leo is now powered by Claude Haiku and available to all users for free
-
GPT-4o versus Llama-3: Local Free AI Model Deployment
By
–
Not really sure, but much less with GPT-4o. Plus, soon I am come up with a version that runs on llama-3 locally. So free of cost.