Aaron

Vibe coded pull requests that basically rewrite every line of code in your repo. Yep, I'm not gonna merge that.

Not so sure about this liquid glass UI. A bit too over done for my liking. More style than substance.

Had my first case of a prospective client get in touch about an app they “vibe coded” (their words) and needing help getting it working. Nah. Fuck that shit. Not touching it with a barge pole.

Ushered Terry Nutkins to his seat at the cinema in west swindon.

"I recommend a hybrid approach..." Claude, just make a frickin decision please.

Question for vibe coders: How do you create/manage your stack-specific context files (.cursorrules etc)? - do you hand-roll them for every project? - or get LLMs to write them? - do you keep a context library for different stacks? - or copy from a website? - is this a PITA that needs a solution?

First ride of the year that wasn’t face-achingly cold. Even a bit of Bluesky™️ on show.

🧠 Just published Anthropix v0.6. Now you can see Claude ✨think✨ about exactly how many R's are in strawberry in unnecessarily impressive depth! github.com/lebrunel/ant... #ai #claude #elixir

I wrote a long and slightly rambling post about the hot new way to code that all the cool kids are doing. 2point0.ai/posts/vibe-c... #ai #coding #vibe-coding

I wrote a long and slightly rambling post about the hot new way to code that all the cool kids are doing. 2point0.ai/posts/vibe-c... #ai #coding #vibe-coding

Everyone I know who codes using LLMs all seem to stick to next/react/shadcn etc. I'm wondering what people's experiences are with other frameworks, eg Vue or Svelte, or even non-JS stacks. Are the models capable enough to veer off the beaten path or are we not there yet?

Had a slightly disappointing week with a work opportunity that, well, didn't work out. Need to do a flex build 💪🏻 to get my mojo back. What should I build?

As a brit watching reports of the LA fires, I have one question: What is so wrong with the word "burgle" that you had to invent "burglarize"?

10 days well spent 👏👏👏

Squeezed in a quick Agentflow release before the weekend! 🚀 New in this release: - Prompt fragments - reusable, composable prompt engineering components - Role attribute - fine-tune agent personas and behaviours Check out the docs: agentflow.2point0.ai/guide/workfl...

This was good fun. I don't even know python (hence first result 😳), but seems a nice way to learn some basics. Leetle #8 2/6 6:38 [8 lines] ⚠️⚠️⚠️⚠️⚠️⚠️ 🟩🟩🟩🟩🟩🟩 leetle.app

Released a nice little update to Ollama-ex. What's new? 1. Finally, generate structured outputs by passing a JSON schema map in a request (requires ollama >= 0.5) 2. Preload and unload models from memory Code: github.com/lebrunel/oll... Docs: hexdocs.pm/ollama #elixir #ollama #buildinpublic

Good morning and happy new year. I love Christmas, but I always descend into completely ferrel eating and sleeping habits, making this day where normality begins to return, one of my favourite days of the year.

I don’t often pay on the Xbox, but when I do, I binge endlessly for days. Indy and the great circle has currently got me 🎮 😍

I shared my work on Agentflow with Bsky last week because you guys are the best... But now I blogged about it so 12 more people are in the know. 2point0.ai/posts/announ...

Remember 6 months ago when everyone was laughing at Google's AI plays. 6 months is a looong time.

Monorepos are all fun and games until someone needs to publish a package 😩

Am I going mad or is NPM borked right now? Can't update packages, can't login, have reset my password, and still can't log in.

Finally, a baked in way of generating structured outputs is coming to Ollama 🙏🏻✨ github.com/ollama/ollam...

On to day 4 of Advent with ML ✅ Started yesterday with embeddings and today we are taking a bit of a break from deep learning to go down a search rabbit hole. Tenuous link to AI/ML but it is used everywhere and not many people know about it.... BM25! mattzcarey.com/blog/advent-...

Astro 5.0 is here. Content layer, server islands, simplified prerendering, type-safe env, @vite.dev v6. All stable. Go see what you can do 👇 astro.build/blog/astro-5/

I know a lot of people (including me) raised their eyebrows when Anthropic increased the price of Haiku... But I've given it a good run-out today and I have to admit, Haiku 3.5 is noticeably more impressive than 3. I'd say Haiku can replace Sonnet for a lot of every day jobs.

Is there such a thing as a ProductHunt-like platform, that specifically is for launching open source products/projects? #buildinpublic

Attitudes to tech will be the big social divide of the future. Left vs right is so 19th century. Forward vs back is where its at now. (divisiveness is toxic no matter who it comes from)

I read recently that X penalises users for posting links, which is why you see this thing of users posting info about a link, and putting the link itself into a reply. I have questions: 1. Is this true, and how do we *know* X penalises this? 2. Is there a logical reason why X does this?

I finally found an AI starter pack for people like me (ie not big-brain ML boffins) - one for devs, builders and hackers: go.bsky.app/UcofkF4

I love the fact that with @bun.sh my moderately sized test suite runs in 300ms ⚡😎

The first bit of pitchfork wielding bluesky controversy I've seen. Again, just like old twitter 😆 Complex issue. I do wonder where the line is where data from a free and inherently open network can be happily used for some things but not others.