Every OpenAI product update kills a bunch of startups & expensive consulting projects. RAG is increasingly being built into core AI model offerings (but RAG is quite limited, and, at times, risky. See halfway though this post: https://
oneusefulthing.org/p/which-ai-sho
uld-i-use-superpowers
…)
AGENTS
-
OpenAI Updates Kill Startups While RAG Becomes Standard
By
–
-
Assistants API Updates: Expanded File Support and Better Control
By
–
Launching a series of updates to the Assistants API—now with support for up to 10,000 files for knowledge retrieval and more precise tool and token control. Excited to see what you build!
-
Optimize Multiple LLM Calls by Mixing Models for Lower Latency
By
–
Most LLM apps and AI Agents need multiple calls to an LLM, especially a moderately complex LLM app/AI agent. Calling GPT-4 or Claude is impractical and you will soon be in high-latency hell. The optimal way to do this is to mix and match LLMs depending on the latency,
-
AI Mentorship Boosts Small Business Profits by 15 Percent
By
–
I would love to see more work on AI as advisor to humans, rather than AI just doing work. This controlled study in Kenya found top small business entrepreneurs got a stunning 15% boost in profits when given an AI mentor, but low performers struggled with mentorship & did worse.
-
HireBorderless RAG-Powered Legal AI Assistant with Cohere
By
–
Learn about the @hireborderless success story in our upcoming webinar on April 30 at 2pm ET! Discover how RAG technology within Cohere’s Command R and Embed model helped them develop a cutting-edge legal AI assistant for global employment. Register here: https://
info.cohere.ai/building-a-rag
-powered-ai-legal-assistant-with-cohere
… -
Moving Goalposts: Redefining Success for AI Software Engineers
By
–
are we so good at moving goalposts that we call it "disappointing" if Devin merely replicated a remote junior software engineer? its up to us to figure out how to use it
-
Following Up on Stream Repos and Temporal Workflow Setup
By
–
following up on some repos from the stream (sorry for delay, merely got lazy) – @yikesawjeez https://
github.com/swyxio/devin-d
ocker-ui/
…
– @studentfoundersclub https://
github.com/swyxio/devin-c
loudflare-upload/
…
– building a @temporalio workflow by reading docs and setting up a local cluster (cant remb who asked for this) -
GPT-4 128k Context Window Now Available for Prompt Bots
By
–
New: GPT-4 128k is now available as a base for prompt bots! The longer context window coupled with the power of the latest GPT-4 update should enable a variety of new use cases. Enjoy! pic.twitter.com/rKsHPQj1mD
— Poe (@poe_platform) 16 avril 2024New: GPT-4 128k is now available as a base for prompt bots! The longer context window coupled with the power of the latest GPT-4 update should enable a variety of new use cases. Enjoy!
-
Madhumita Murgia discusses CODE DEPENDENT human agency and AI
By
–
I’ll be in Cambridge on Saturday, in conversation with @ginasue about my book CODE DEPENDENT and its themes of human agency and power in an age of
AI – come say hi! Details here: https://
cambridgeliteraryfestival.com/events/madhumi
ta-murgia/
… -
Code Interpreter Hidden Features Discrepancy Analysis
By
–
Yeah I'm still suspicious about that, because there are features of code interpreter (like the ability to provide a link to download a file) that aren't mentioned in the system prompt for it