venturebeat

2025-10-02

New AI training method creates powerful software agents with just 78 examples

A new study by Shanghai Jiao Tong University and SII Generative AI Research Lab (GAIR) shows that training large language models (LLMs) for complex, autonomous tasks does not require massive datasets.

Their framework, LIMI (Less Is More for Intelligent Agency), builds on similar work in other areas of LLM research and finds that “machine autonomy emerges not from data abundance but from strategic curation of high-quality agentic demonstrations.” 

In other words, it's data quality, not quantity, that matters.

In experiments, the researchers found that with a small, but carefully curated, dataset of just 78 examp [...]

Rating

Innovation

Pricing

Technology

Usability

We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.

Destination

2025-05-26

Skullcandy Method 360 ANC review: A cheaper version of Bose’s best earbuds, with a few key sacrifices

Skullcandy isn’t a name that usually comes to mind when you think of premium headphones. The Utah-based company has primarily made its name in the budget space, selling more on low prices and loud, [...]

Match Score: 99.28

Destination

2025-02-28

Engadget Podcast: iPhone 16e review and Amazon's AI-powered Alexa+

The keyword for the iPhone 16e seems to be "compromise." In this episode, Devindra chats with Cherlynn about her iPhone 16e review and try to figure out who this phone is actually for. Also, [...]

Match Score: 70.93

Destination

2025-07-10

How exactly did Grok go full 'MechaHitler?'

Earlier this week, Grok, X's built-in chatbot, took a hard turn toward antisemitism following a recent update. Amid unprompted, hateful rhetoric against Jews, it even began referring to itself as [...]

Match Score: 56.71

Destination

2025-09-28

Study claims 78 training examples are enough to build autonomous agents

A new study challenges a core assumption in AI: instead of massive datasets, just 78 carefully chosen training examples may be enough to build superior autonomous agents.<br /> The article Study [...]

Match Score: 55.64

venturebeat

2025-10-01

Thinking Machines' first official product is here: meet Tinker, an API for distributed LLM fine-tuning

Thinking Machines, the AI startup founded earlier this year by former OpenAI CTO Mira Murati, has launched its first product: Tinker, a Python-based API designed to make large language model (LLM) fin [...]

Match Score: 51.60

engadget

2025-10-01

Peloton updates its Bike, Tread and Row machines with form-checking cameras, rotating screens and lots of AI

It’s been a rough time for Peloton. Last year was marred by deep staff cuts, a change of CEO and a reckoning of where the home fitness company belonged, post-Pandemic boom. The answer is, unfortunat [...]

Match Score: 51.19

venturebeat

2025-10-01

Slack is giving AI unprecedented access to your workplace conversations

Slack is fundamentally reshaping how artificial intelligence agents access and use enterprise data, launching new platform capabilities that allow developers to tap directly into the rich conversation [...]

Match Score: 45.37

Destination

2025-06-14

New method adapts language models without training

Researchers at Sakana AI have introduced Text-to-LoRA (T2L), a method that adapts large language models to new tasks using only a simple text description - no extra training data required.<br /> [...]

Match Score: 42.92

venturebeat

2025-10-06

OpenAI unveils AgentKit that lets developers drag and drop to build AI agents

OpenAI launched an agent builder that the company hopes will eliminate fragmented tools and make it easier for enterprises to utilize OpenAI’s system to create agents. AgentKit, announced during Ope [...]

Match Score: 42.79