
🤔 I'm not sure this will be my forever home, but for now, I'm also on Mastodon for anyone who is into that. 🔥 Worse case I will mirror my tweets, and best case I will eventually run my own identity server, but for now: mastodon.social/@webology

Python, Django, Docker, Engineer, Partner at @revsys - Affiliations @ThePSF @defnado @djangocon @djangoproject - @webology@mastodon.social

🤔 I'm not sure this will be my forever home, but for now, I'm also on Mastodon for anyone who is into that. 🔥 Worse case I will mirror my tweets, and best case I will eventually run my own identity server, but for now: mastodon.social/@webology

Interested in personal agents like Hermes and other fun things to do with AI? Jeff Triplett was on the Talk Python podcast recently to talk to Michael Kennedy all about it youtube.com/watch?v=ZfV5G5Es…

Pydantic AI now turns on prompt caching with one capability. Anthropic and Bedrock cache nothing unless the request asks. The Caching capability asks for you: tool definitions, instructions and the conversation, one setting instead of each provider's. pydantic.io/uJC8d

The launch discount for Dinkus ends at the end of the month. Post Monday, it is full price. Dinkus is a visual Markdown editor for macOS. Author and edit Markdown files with an intuitive GUI. Switch to raw markdown when you need it. No account or subscription. Always local. 🧵 dinkus.textualize.io/

Not going to make it to Chicago for DjangoCon US 2026? That's ok, I mean I'll miss you, but did you know you can watch all of the talk lives for cheap? Grab a ticket and help support the conference and community! ti.to/defna/djangocon-us-202… #django #python

You may have been told to watch this video about the OpenAI AI hack. You really should, even if you don't usually care about tech stuff. If nothing else, click this link to the 18 minutes in & see how the agents spoke with each other. Its eye opening. youtu.be/87DyyMV0kCY?si=DMfq…

I got nothing to sell you, but out of frustration, I updated GLM-Launch as an alternative while Claude sucks. github.com/jefftriplett/glm-… I'm tempted to write a Kimi-K3 which also doesn't suck. I miss good Claude, not crappy Claude though. #glm #claudecode #claude #llm

Opus 5 has been a bust for me. I understand why, but two to three days before every major @AnthropicAI release, their models get incredibly dumb. Then for 2 to 5 days post-release, it takes them time to adjust Claude Code and their servers so they don't suck. Today, they suck.
Welp, back to Fable. I'm done with Opus 5 as a collaborator. Opus 5 is still just Opus: blustering and often wrong. Fable is the only enterprise-grade model on the market today. The rest of them cannot be trusted. If you're an engineer at an enterprise who's pissed off at how bad AI is, then you're right -- it is all bad. Except Fable itself, which is good enough, but too expensive to be practical. The world isn't going to have good-enough cheap-enough models for a while, it would seem.

This is how you respect your users. Unlike what the US companies do by over-provisioning time and time again.
Kimi K3 has received far more love than we expected, and our GPUs are feeling it. Over the past 48 hours, demand has pushed close to the limits of our current capacity. To protect the experience of existing subscribers, we're temporarily pausing new subscriptions and prioritizing compute for current members. Existing subscribed users are not affected. We're adding capacity as fast as we can and will reopen new subscription spots in batches. Going forward, we'll also split membership into two more focused plans: Kimi Membership for Kimi Web, App, and Work; and Kimi Code Membership for coding workflows. This will help us match compute more precisely and keep the experience stable. Thank you for your patience and understanding!

This is the friendliest and bestest open source conference out there. Join us!
🎤 Speaker Spotlight Elizabeth Christensen joins DjangoCon US 2026 with: "What's New in Postgres 18 & 19" Learn which new PostgreSQL features are ready for your Django apps and which ones can wait. #Django #Python #PostgreSQL

🚀 Using Claude Code or Codex with GLM 5.2 can be a bit of a pain. I built a small launcher for GLM 4.5/4.6 back in December, but never published it because I assumed it was no longer useful. I released it tonight as glm-launch. github.com/jefftriplett/glm-… #ClaudeCode #Codex

Jeff has been telling me about this setup for awhile and I finally took the time to get it going today. Integrated with Zellij in the most amazing way. Definitely recommended for on the go prompting! micro.webology.dev/2026/06/1…

🤔 Death, taxes, and GitHub's status page being red... githubstatus.com

📋Take the 2026 #Django Developers Survey! Help guide future technical and community decisions - find out more at the link: djangoproject.com/weblog/202…

The PyCharm - Django promo also works with renewals. So if you are already using PyCharm, consider renewing with this promo! jetbrains.com/pycharm/promo/… Get 30% off PyCharm Pro, with 100% of the proceeds going to the Django Software Foundation. #Django #Python

GitHub stars are only good for measuring GitHub stars and nothing more. It's been like that for almost a decade. Now it's even more of a meaningless metric.
Github stars were a great way to see how popular a project was. Now they're mostly a way for companies to trick VCs into investing. The hidden economy around all of it is super wild. Obviously had to do a video about it