Blog
Daily notes on new models, LLM releases, agent frameworks and AI research, written from the sources we follow and delivered as a newsletter every day.
Get the daily issue
Every new post of the day, in one email. Confirmation required.
Models1 min read
Perplexity utilizes GPT-6 Astra to manage communications, software changes, and production system monitoring. This approach reduces the frequency of checks compared to previous models.
From OpenAI news
LLMs1 min read
OpenRouter automatically selects the most cost-effective backend provider for model requests, handling variations in serving software and capabilities. Using the provider.only option allows control over routing for specific model IDs.
From Simon Willison
How this blog is made
Each feed entry becomes one request to OpenSmartRoute: the router picks a model with a cost-weighted objective, the editorial-writer skill is layered on the prompt, and the outcome trains the learners - the same pipeline available to every workspace.
Open any post to see which target answered, its confidence, the alternatives and what the request cost. Run the same pipeline yourself: register feeds in the operator console, map a small model under Providers, or call POST /api/v1/route with execute: true.
LLMs1 min read
My comment on Feeling sad about AI — Hacker News. I'm not sure how useful it is to say this, but I think a lot of people (myself included, a few years ago now) have been through this moment of existential crisis and come out the other si...
From Simon Willison
Models1 min read
OpenAI’s GPT-6 Astra improves Devin’s ability to test software and verify functionality. This allows engineers to reduce code review efforts and accelerate software delivery.
From OpenAI news
LLMs1 min read
Replacing old systems with new ones often leads to dual systems in production, with ongoing risks and incomplete replacements. Automated testing and targeted refactors can improve success chances.
From Simon Willison
LLMs1 min read
Zach Kehs highlights that unlike physical structures, software can always degrade through added layers or reduced performance, emphasizing ongoing technical debt risks.
From Simon Willison
LLMs1 min read
Paint.NET now uses an internal, reverse-engineered version of Direct2D on WINE, developed by Claude, to bypass incomplete support. The code is unreviewed and relies on trust.
From Simon Willison
AI1 min read
Julia has millions of users worldwide, supporting research and development in fields like drug design and engineering.
From MIT News: artificial intelligence
LLMs1 min read
A perception stack is shaped by the vehicle that carries it. Move the same software to a new carline—for example, from an SUV to a sedan or another vehicle...
From NVIDIA technical blog
LLMs1 min read
NVIDIA NVLink Fusion expands NVHBM capabilities, allowing for increased bandwidth and reduced latency between GPUs. This facilitates the execution of larger AI models and complex reasoning workloads within next-generation AI infrastructure.
From NVIDIA technical blog
Models1 min read
loveholidays uses OpenAI Codex to enable teams to develop software more quickly and efficiently across the business.
From OpenAI news
Models1 min read
OpenAI's CFO highlights how improvements across hardware and software components enable more scalable and cost-effective AI solutions.
From OpenAI news
Posts are drafted from public feeds by models OpenSmartRoute routes to - the same router, skill and metering customers use - and always link to the original source. Corrections: support.
