Sublime
An inspiration engine for ideas
This Agentic Deep Research beats Perplexity and GPT-4.5 on OpenAI’s SimpleQA benchmark.
Multiple AI Agents break down questions, search trusted sources, and deliver visual insights you can export in various formats.
At just 3% of Perplexity's funding. https://t.co/kNFvSqaJJr
Shubham Saboox.comWriting assistant, workhorse, or accelerator? How academics are using GenAI
Mads P. Sørensenblogs.lse.ac.uk
Multi-agent app to transform any research paper into a code repository.
It follows a 3-stage pipeline handled by specialized AI Agents:
- Planning
- Analysis
- Code Generation
100% Opensource. https://t.co/FPYgX0dvub
o3-mini researcher
Give it a topic, use o3-mini for report planning w/ human feedback, then parallelize all research/writing when plan is accepted. All open source (code below)
Lance Martinx.com
Introducing Deep Research on Perplexity.
Deep Research lets you generate in-depth research reports on any topic.
Available to everyone for free—up to 5 queries per day for non-subscribers and 500 queries per day for Pro users. https://t.co/obovx7YEUF
Perplexityx.comMaster Plan
In short, PARPA's master plan is:
In short, PARPA's master plan is:
- Create and stress-test unintuitive research programs in a systematic (and therefore repeatable) way.
- Use that credibility to run a handful of research programs and produce results that wouldn't happen otherwise.
- Use that credibility to run more research programs and help them "graduate" to effective
Shifting the imposible to the inevitable: A Private ARPA user manual
This is that original MIT report that said 95% of AI pilots fail and which spooked investors across US Stockmarket.
The reports says, most companies are stuck, because 95% of GenAI pilots produce zero ROI, while a small 5% win by using systems that learn, plug into real workflows, and improve with use.
__... See more