Web & AI Analyst
This section contains republished articles from my journalism career, including work for The New Stack, Newsroom, and Stuff.co.nz.
Coder, the self-hosted “Cloud Development Environment” (CDE) has just announced version 2.0 of its product, which includes new Dev Container support and integration with JFrog’s artifact repository. To discuss the latest in Coder.com, I spoke to co-founder and CTO Kyle Carberry and new CEO Robert Whiteley. When it comes to CDEs, SaaS products like GitHub … Read more
Meta’s recent release of Code Llama, a large language model (LLM) for code generation, prompted the data cloud company Snowflake to evaluate Code Llama’s performance on SQL code generation. It found that “Code Llama models outperform Llama2 models by 11-30 percent accuracy points on text-to-SQL tasks and come very close to GPT4 performance.” Snowflake also … Read more
Codeanywhere was one of the first web-based code editors when it was released in 2009 (as PHPanywhere). Since that time, entire developer environments have migrated to the cloud and Codeanywhere has found itself slipping behind in the ultra-competitive Cloud IDE market, where newer products like GitHub Codespaces and Replit have taken center stage. To rectify … Read more
Few companies have had a bigger impact on the frontend developer ecosystem in the 2020s than Vercel, steward of the popular React framework, Next.js. When I first wrote about Vercel, in July 2020, the company had just embraced the Jamstack trend and was liberally using the term “serverless” in its marketing. But with Jamstack on … Read more
In the evolving LLM app stack, a British company called Humanloop has — perhaps accidentally — defined a new category of product: an LLM “playground.” It’s a platform where developers can test various LLM prompts, and then deploy the best ones into an application with full DevOps-style measurement and monitoring. To understand exactly what Humanloop … Read more
Earlier this week, Matt Rickard wrote a post entitled “Why Tailwind CSS Won,” which got to the front page of Hacker News. Inevitably, it kicked off the latest round of polarized opinions on social media about a popular web development tool. Surprise, surprise: some people love Tailwind, and others hate it. The reasonings for each … Read more
The developer ecosystem for AI-enabled applications is beginning to mature, after the emergence over the past year of tools like LangChain and LlamaIndex. There’s even now a term for AI-focused developers: AI engineer, which is the next step up from “prompt engineer,” according to its proselytizer Shawn @swyx Wang. He’s created a nifty diagram showing … Read more
When Netlify acquired one of its former competitors, Gatsby, in February, I noted that its use of the term “Jamstack” (which it coined in 2016) wasn’t so prominent in its marketing anymore. “Composable architectures” appeared to be the new catchphrase. Fast-forward six more months, and Netlify has just closed The Jamstack Community Discord, according to … Read more
Over the weekend, I ran a poll on Mastodon that asked the following question: “If Threads goes ahead with its plan to add ActivityPub, will you follow one or more Threads users in your Mastodon account?” The poll received 3,889 replies before closing (helped by a “boost” from Mastodon creator Eugen Rochko), so it was … Read more
From a developer point of view, the fact that Meta’s Threads app has quickly gone over 100 million sign-ups isn’t the most interesting part of this latest Twitter clone. More intriguing is Meta’s promise to make Threads a part of the fediverse, by adding support for the World Wide Web Consortium (W3C) ActivityPub specification. The … Read more
What if you could combine your own private data store with a large language model (LLM) like OpenAI’s GPT, and query it programmatically? That’s the promise of LlamaIndex, a new framework that helps developers avoid fine-tuning and overly long prompts. It’s part of an emerging category of LLM application tools that some are calling “orchestration … Read more
When Adobe announced that it would acquire the design tool Figma for $20 billion last September, an open source equivalent called Penpot immediately began seeing a spike in signups. Penpot, which is developed by a Spanish company called Kaleidos, continued to grow rapidly after it launched General Availability in February. Since then, Penpot sign-ups have … Read more
MosaicML is launching its second open source large language model (LLM), called MPT-30B, which follows on from the smaller MPT-7B model it debuted in May. To discuss the new model and what it means for developers, I spoke to MosaicML co-founder and CEO, Naveen Rao. His previous startup was Nervana, a deep learning company that … Read more
Forget the LAMP stack, it’s now all about the LLM stack. Tools such as LangChain and Anyscale’s Aviary have launched over the past year to help developers build apps based on — or connected to — large language models (LLMs). Although it’s still early days, Hugging Face has quickly become a key part of this … Read more
Today at Canva’s first-ever developer conference in San Francisco, the company announced a new developer platform, along with a $50 million “Innovation Fund.” Canva, a design platform that competes with the likes of Adobe and Figma, claims it has 135 million monthly active users. So this is potential of great interest to devs — including … Read more