Ben from the Future (@agileben) 's Twitter Profile
Ben from the Future

@agileben

Founder Freshwater Futures | AI Discovery, Rapid Prototypes and AI Engineering

ID: 79113237

linkhttps://freshwaterfutures.com calendar_today02-10-2009 06:26:16

1,1K Tweet

1,1K Takipçi

1,1K Takip Edilen

Eric Jing (@ericjing_ai) 's Twitter Profile Photo

Seeing AGI - Eric Jing • Jun 2, 2025 "AI will impact 99% of people's jobs, and white-collar jobs might be wiped out. New graduates might be unemployed on day one. It deserves our closest attention—not just for ourselves, but for our children." This may not be a post that many

Alex Albert (@alexalbert__) 's Twitter Profile Photo

Multi-agents systems are the next frontier of AI applications. At Anthropic, we found that multi-agents beat single agents by up to 90%+ on some complex tasks. We wrote a blog post detailing practical tips for building multi-agent systems based on our own experiences:

Multi-agents systems are the next frontier of AI applications. At Anthropic, we found that multi-agents beat single agents by up to 90%+ on some complex tasks.

We wrote a blog post detailing practical tips for building multi-agent systems based on our own experiences:
Logan Kilpatrick (@officiallogank) 's Twitter Profile Photo

Today we are rolling out Imagen 4 and Imagen 4 Ultra in the Gemini API + Google AI Studio! Available to try for free in AI Studio and in paid preview in the API.

Today we are rolling out Imagen 4 and Imagen 4 Ultra in the Gemini API + Google AI Studio! Available to try for free in AI Studio and in paid preview in the API.
Andrej Karpathy (@karpathy) 's Twitter Profile Photo

+1 for "context engineering" over "prompt engineering". People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. When in every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window

Drew Breunig (@dbreunig) 's Twitter Profile Photo

I went down a rabbit hole of context engineering / context management techniques when building LLM applications. Everything I read can be bucketed into these 6 core tactics 📑RAG 🧰Tool Loadout 🫙Context Quarantine ✂️Context Pruning 📝Context Summarization 🗄️Context Offloading

Charly Wargnier (@datachaz) 's Twitter Profile Photo

Insane. Stanford University just dropped Co-STORM, an AI tool that writes research papers like a PhD! 🤯 - 99% factual accuracy - Cited sources (with references) - Completely free Type a topic → it reads the web → you get a polished, cited PDF report. repo and free app in 🧵↓

Dan Mac (@daniel_mac8) 's Twitter Profile Photo

🔥 Google announced: Gemini Embeddings a cost effective embeddings model at $0.15/mil tokens few things you can implement with it: >> semantic search >> doc classification and tagging >> recsys don't sleep on the embeddings models y'all

🔥 Google announced: Gemini Embeddings

a cost effective embeddings model at $0.15/mil tokens

few things you can implement with it:

>> semantic search
>> doc classification and tagging
>> recsys

don't sleep on the embeddings models y'all
Groq Inc (@groqinc) 's Twitter Profile Photo

OpenAI’s open models are live and already running on Groq. Try gpt-oss-20B and gpt-oss-120B today. Groq delivers 128K context and built-in tools such as code execution and browser search. For the first time, developers and enterprises can deploy open models backed by OpenAI

Claude (@claudeai) 's Twitter Profile Photo

Claude Sonnet 4 now supports 1 million tokens of context on the Anthropic API—a 5x increase. Process over 75,000 lines of code or hundreds of documents in a single request.

Claude Sonnet 4 now supports 1 million tokens of context on the Anthropic API—a 5x increase.

Process over 75,000 lines of code or hundreds of documents in a single request.