Just as there are widely understood empirical laws of nature - for example, what goes up must come down, or every action has an equal and opposite reaction - the field of AI was long defined by a single idea: that more compute, more training data and more parameters makes a better AI model.
However, AI has since grown to need three distinct laws that describe how applying compute resources in different ways impacts model performance. Together, these AI scaling laws - pretraining scaling, post-training scaling and test-time scaling, also called long thinking - reflect how the field has evolved with techniques to use additional compute in a wide variety of increasingly complex AI use cases.
The recent rise of test-time scaling - applying more compute at inference time to improve accuracy - has enabled AI reasoning models, a new class of large language models (LLMs) that perform multiple inference passes to work through complex problems, while describing the steps required to solve a task. Test-time scaling requires intensive amounts of computational resources to support AI reasoning, which will drive further demand for accelerated computing.
What Is Pretraining Scaling? Pretraining scaling is the original law of AI development. It demonstrated that by increasing training dataset size, model parameter count and computational resources, developers could expect predictable improvements in model intelligence and accuracy.
Each of these three elements - data, model size, compute - is interrelated. Per the pretraining scaling law, outlined in this research paper, when larger models are fed with more data, the overall performance of the models improves. To make this feasible, developers must scale up their compute - creating the need for powerful accelerated computing resources to run those larger training workloads.
This principle of pretraining scaling led to large models that achieved groundbreaking capabilities. It also spurred major innovations in model architecture, including the rise of billion- and trillion-parameter transformer models, mixture of experts models and new distributed training techniques - all demanding significant compute.
And the relevance of the pretraining scaling law continues - as humans continue to produce growing amounts of multimodal data, this trove of text, images, audio, video and sensor information will be used to train powerful future AI models.
Pretraining scaling is the foundational principle of AI development, linking the size of models, datasets and compute to AI gains. Mixture of experts, depicted above, is a popular model architecture for AI training. What Is Post-Training Scaling? Pretraining a large foundation model isn't for everyone - it takes significant investment, skilled experts and datasets. But once an organization pretrains and releases a model, they lower the barrier to AI adoption by enabling others to use their pretrained model as a foundation to adapt for their own applications.
This post-training process drives additional cumulative demand for accelerated computing across enterprises and the broader developer community. Popular open-source models can have hundreds or thousands of derivative models, trained across numerous domains.
Developing this ecosystem of derivative models for a variety of use cases could take around 30x more compute than pretraining the original foundation model.
Developing this ecosystem of derivative models for a variety of use cases could take around 30x more compute than pretraining the original foundation model.
Post-training techniques can further improve a model's specificity and relevance for an organization's desired use case. While pretraining is like sending an AI model to school to learn foundational skills, post-training enhances the model with skills applicable to its intended job. An LLM, for example, could be post-trained to tackle a task like sentiment analysis or translation - or understand the jargon of a specific domain, like healthcare or law.
The post-training scaling law posits that a pretrained model's performance can further improve - in computational efficiency, accuracy or domain specificity - using techniques including fine-tuning, pruning, quantization, distillation, reinforcement learning and synthetic data augmentation.
Fine-tuning uses additional training data to tailor an AI model for specific domains and applications. This can be done using an organization's internal datasets, or with pairs of sample model input and outputs.
Distillation requires a pair of AI models: a large, complex teacher model and a lightweight student model. In the most common distillation technique, called offline distillation, the student model learns to mimic the outputs of a pretrained teacher model.
Reinforcement learning, or RL, is a machine learning technique that uses a reward model to train an agent to make decisions that align with a specific use case. The agent aims to make decisions that maximize cumulative rewards over time as it interacts with an environment - for example, a chatbot LLM that is positively reinforced by thumbs up reactions from users. This technique is known as reinforcement learning from human feedback (RLHF). Another, newer technique, reinforcement learning from AI feedback (RLAIF), instead uses feedback from AI models to guide the learning process, streamlining post-training efforts.
Best-of-n sampling generates multiple outputs from a language model and selects the one with the highest reward score based on a reward model. It's often used to improve an AI's outputs without modifying model parameters, offering an alternative to fine-tuning with reinforcement learning.
Search methods explore a range of potential decision paths before selecting a final output. This post-training technique can iteratively improve the model's responses
Most recent headlines
05/01/2027
Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be ...
06/09/2026
June 9 2026, 23:00 (PDT) Dolby and MagentaTV Bring Fans Closer to the FIFA Worl...
04/08/2026
Dalet, a leading technology and service provider for media-rich organizations, t...
04/07/2026
April 7 2026, 19:00 (PDT) Detective Conan: Fallen Angel of the Highway Opens in...
03/07/2026
New bundle & three Single Packs
Continuing to expand their already sizeable orchestral collection, VSL's latest release introduces three new Single Pack...
03/07/2026
Venue installs new ATC-equipped control room
LSO St Luke's, a unique music venue that also serves as the home of the London Symphony Orchestra, have rec...
03/07/2026
Caden Pearson appointed new Commissioning Editor for NITV
3 July, 2026
Media releases
National Indigenous Television (NITV) has strengthened its commitment...
03/07/2026
1 February 2023
SHARE Facebook Twitter Linkedin Email
Munich, Germany, 1st February 2023: Cinegy GmbH, the premier provider of software technology for digit...
03/07/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
03/07/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
03/07/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
03/07/2026
Death Star
Andy Marken July 2, 2026
0 Comments
Look, I can't get involved. I've got work to do. It's not that I like the Empire; I hate i...
03/07/2026
Berklee's New Visual Identity: Honoring Our History, Building for What's...
03/07/2026
Scripps Research scientists awarded $2M to advance global disease surveillance Two Gates Foundation grants will expand wastewater surveillance and AI-driven dis...
03/07/2026
Joan Pulupa joins Scripps Research faculty to study the organization of DNA in brain cells and its links to neurodegeneration Using smell-sensing neurons and ad...
02/07/2026
Entering her senior year, this hometown girl is paving a career in live sports production gaining experience in replay and audio and as a TD
In the live-sports...
02/07/2026
In-venue and creative video staffers at the professional and collegiate level ha...
02/07/2026
BLAST, a competitive entertainment company focused on esports, has announced more than $133 million in revenue for 2025, representing more than 40% year-over-ye...
02/07/2026
Riedel Communications has announced official SKAARHOJ panel support for SimplyLive production workflows, enabled through the SimplyLive 2.1 release. The integra...
02/07/2026
The Fire Rescue Service of the Czech Republic has deployed LiveU video-over-bond...
02/07/2026
Gravity Media USA has announced the appointment of Brittney Boston as Head of Business Development, effective July 1, 2026. Based in Nashville, Tennessee, Bosto...
02/07/2026
TwelveLabs, a video intelligence company, has announced $100 million in Series B funding co-led by NEA and NAVER Ventures, with participation from Amazon, Radic...
02/07/2026
The Pro Padel League (PPL) has announced a broadcast partnership with USA Sports that will air five PPL championship matches on CNBC during the 2026 season, the...
02/07/2026
LiveLike, a digital fan engagement platform, has announced eight confirmed FIFA ...
02/07/2026
Cobalt Digital has received Future's Best of Show Award, presented by AV Technology at InfoComm 2026, for its blueCORE family of standalone signal processor...
02/07/2026
Synamedia has announced the appointment of Dr. Tzvi Gerstl as Chief Executive Officer. Paul Segre, who has served as CEO for the past six years, will transition...
02/07/2026
The Esports Foundation (EF) and Sony Group Corporation have announced an expanded collaboration for the Esports World Cup 2026 (EWC), taking place in Paris, Fra...
02/07/2026
Zee Entertainment Enterprises Ltd. ( Z') has announced exclusive broadcast and digital rights for the Bundesliga in India for five years, beginning with the...
02/07/2026
An effort uniting News, Sports, Local, and Telemundo, the 50+-camera live produc...
02/07/2026
Zoey Deutch, John Slattery, Ken Marino, Miles Gutierrez-Riley, and Ben Wang appe...
02/07/2026
Stammering, stuttering, strangulated tones
The Crow Hill Company's latest creation promises to be the most original sound set they've produced to d...
02/07/2026
A new era in unmixing and spectral editing
The latest version of Steinberg's spectral audio-editing software has just arrived, building on the strength...
02/07/2026
Aims to simplify additive synthesis
Sine Machine is the debut launch from Melatonin, a Vienna-based developer who have spent the past six years creating wha...
02/07/2026
Products to remain fully active & supported
Following the news of Native Instruments joining the inMusic brand line-up, Academy and Emmy Award-winning visua...
02/07/2026
What you missed!
Last weekend, Saturday 27 June 2026, saw the debut of Sound On Sounds new GearExpo UK event, the largest dedicated pro-audio event to take ...
02/07/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
02/07/2026
Following the successful launch of its inaugural APAC Mentoring Programme last month, the Rise AV APAC Regional Council will bring the conversation around mento...
02/07/2026
Blackmagic PYXIS 6K Used to Shoot Director Takahisa Zeze's Cry Out
Brie Clayton July 2, 2026
0 Comments
Highly mobile camera supports tense and de...
02/07/2026
Broadcast Solutions acquires BFE, expanding its lead in European broadcast, medi...
02/07/2026
Berklee Alum and Faculty Perform at Boston Public Library's 250th Anniversar...
02/07/2026
Broadcast Solutions GmbH, a leading systems integrator and provider of innovative solutions for the broadcast media industry, is acquiring BFE Studio und Medien...
02/07/2026
Cinegy GmbH, the premier provider of software-defined television technology, has extended the ingest facility at leading Brazilian sports company LiveMode, work...
02/07/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
02/07/2026
Standalone processors acknowledged for the innovation and value they bring to Pro AV
Cobalt Digital, a leading designer and manufacturer of signal processing ...
02/07/2026
Synamedia announced today the appointment of Dr Tzvi Gerstl as Chief Executive Officer. Paul Segre, who has served as CEO for the past six years, will transitio...
02/07/2026
Screen Australia backs audience-led filmmaking with new insight-driven initiativ...
02/07/2026
Screen Australia refines guidelines for Narrative Content Development and Docume...
02/07/2026
Maxon Autograph: Introduction to working with Tables
Simon Ubsdell July 1, 2026
0 Comments
An overview of Autograph's ridiculously powerful tables...
02/07/2026
Boston Conservatory's Soir e Breaks Records to Fund Student Scholarships The event achieved 127 percent of its fundraising goal in an evening celebrating ...
Just as there are widely understood empirical laws of nature - for example, what goes up must come down, or every action has an equal and opposite reaction - the field of AI was long defined by a single idea: that more compute, more training data and more parameters makes a better AI model.
