Dan Murfitt

Software engineer, tech geek, fair weather photographer and occasional blogger. Views are my own.

[Dan Murfitt @danmurf]

More and more, I find that getting the best out of AI comes down to learning to trust it the right amount, given the task and your capability to utilise it. These things are also highly dynamic and need constant reevaluation.

[Dan Murfitt @danmurf]

@unclebobmartin I've never seen anything like it! Such a great way to impress through demonstration of engineering capability.

[Dan Murfitt @danmurf]

I wonder whether the success people have with AI coding is largely down to the language and/or framework they choose to use. E.g. using an opinionated framework vs rolling your own. Well known, opinionated frameworks maybe give agents the path to creating more predictable output.

[Dan Murfitt @danmurf]

https://t.co/MugBtW5LKv

[Dan Murfitt @danmurf]

@ollama > If you’re on an existing Pro, Max, or Team plan, your plan continues to work as-is. You can upgrade to the new pricing anytime in your Ollama account settings.

Does switching to the new pricing plan change the rate at which my usage will be consumed, or just how it's reported?

[Dan Murfitt @danmurf]

This is awesome! Your only limit now is your imagination.

[Angel 🌼 @Angaisb_]

I asked GPT-6 Astra to make a portfolio inside a console similar to a Gameboy and LOOK AT THIS

It's so so so good, a huge jump from GPT-5.6

[Dan Murfitt @danmurf]

@AILostMedia for some reason I can’t not see these as Pizza Nuggets!

[Dan Murfitt @danmurf]

@ThePrimeagen 3 months into 6 months away from AGI before GTA 6

[ollama @ollama]

GLM 5.3 and GLM 5.3 Flash (previously Ox Alpha) are fully rolled out on Ollama's cloud.

Private.
Fast.
US and Europe hosted.
Zero data retention.

GLM 5.3:
ollama launch claude --model glm-5.3:cloud

GLM 5.3 Flash:
ollama launch opencode --model glm-5.3-flash:cloud

Works with many more harnesses, or create an API key and plug it straight into your own app.

Which harness should we add next?

[Dan Murfitt @danmurf]

Now is the time to go and build something!

[OpenCode @opencode]

Ox Alpha (stealth model) is free for the next week

- 1M Context
- Multi-modal
- Zero Data Retention

Generous rate limits, near unlimited usage

We have capacity for 100T tokens per day, lets see what you can do

[Paul Graham @paulg]

The trouble with having Zane Hengsperger visit your house is that instead of the usual random house gift, he brings you a 10 pound block of solid aluminum.

[Dan Murfitt @danmurf]

@virginmedia @virginmedia good morning, are you able to confirm if this has now been fixed please?

[Dan Murfitt @danmurf]

@virginmedia I can’t seem to watch any of the Sky Sports+ channels. Can see others have the same problem too. When will this be fixed? Thanks

[Dan Murfitt @danmurf]

@MatthewBerman It’s a shame there isn’t an easy way to pool together and get some sort of peer to peer approach where we all offer a fragment of our personal compute in exchange access to the wider network.

[Dan Murfitt @danmurf]

I feel like I really need to justify using the top tier model when the cheaper equivalent does a good enough job a lot of the time.

[Dan Murfitt @danmurf]

@FluidVoiceApp @Jason @theaaron @WisprFlow Wait, what! You have an iOS app too? Love the desktop app btw! Saving me tons of time! ❤️

[Dan Murfitt @danmurf]

@TheAhmadOsman Nice! What work are you giving to each model? I haven’t play with Qwen 3.8 27B yet but very impressed with DeepSeek V4 Flash.

[Dan Murfitt @danmurf]

@virginmedia I can watch it on my mobile but this is very disappointing.

[Dan Murfitt @danmurf]

There’s a great video which explains how to add a watermark to AI generated output https://t.co/rgR18MDPBq This uses the technique from the paper “A Watermark for Large Language Models” https://t.co/bKhpkQPz7W I imagine Anthropic is using this or a similar method to watermark.