James Hall

It’s always a good sign when the venue tells you you’re playing Daft Punk too loud and it’s affecting the screening of Minecraft next door.

*turns it up louder*

01.05.2025 15:19 — 👍 15    🔁 5    💬 1    📌 0

A screen at the front of a stage at a conference showing live captioning. It reads, “[Hope you had a nice lunch… captioned took a nap]”

Live-captioning a tech conference from another timezone must be knackering!

Happy to see this from our wonderful stenographer at #AllDayHey.

01.05.2025 14:26 — 👍 13    🔁 2    💬 1    📌 1

Carl Sagan explains how the ancient Greeks knew the Earth was round and calculated its circumference over 2,000 years ago.

20.04.2025 17:00 — 👍 16913    🔁 3348    💬 405    📌 265

How to plan and run a discovery workshop What is a discovery workshop and how can they be used to work through problems in your business? In this episode, James and Josh discuss how they've run them in the past and offer some tips and tricks...

I learnt so much from this chat with @mrjameshall.bsky.social on running discovery workshops, if you're looking to host one it's definitely worth a listen.

26.03.2025 12:13 — 👍 6    🔁 1    💬 0    📌 0

🆘Bill Cole 🇺🇦 (@grumpybozo@toad.social) @jwz@mastodon.social The stats we collect for the #SpamAssassin project (mass-scan results from participating sites) have long shown that spammers are more consistent at making SPF, DKIM, and DMARC co...

Spammers are better at SPF, DKIM, and DMARC than everyone else. Which makes them entirely useless signals to use to block mail.

Great work everyone 😂

toad.social/@grumpybozo/...

25.03.2025 10:48 — 👍 3    🔁 0    💬 1    📌 0

Getting your head around sampling (and constrained sampling - like used for Structured Outputs) is a good area to get stuck into.

04.01.2025 12:45 — 👍 1    🔁 0    💬 0    📌 0

- Built a basic UI on top of this to start exploring.

Some interesting advantages to having greater insight into underlying probabilities is knowing when it might be wrong, debugging models issues, and for learning purposes.

04.01.2025 12:45 — 👍 1    🔁 0    💬 1    📌 0

What I've done:
- Pulled Llama3.3 locally from HuggingFace, converted it to GGUF for llama.cpp.
- Quantized it so it doesn't crash my M3 Mac.
- Started a llama.cpp server, and use the raw (non-OpenAI-compatible) API to delve into the underlying logprob data.

04.01.2025 12:45 — 👍 1    🔁 0    💬 1    📌 0

Another weekend project, I've built another visualisation.

Commercial LLMs often don't expose their logits/logprobs. This is the chance that the next token/word appears.

04.01.2025 12:45 — 👍 1    🔁 0    💬 1    📌 0

Add your own words or compare predefined sets.

I'm working on a way to visualise the famous king - man + woman = queen example. Any other ideas?

27.12.2024 17:13 — 👍 1    🔁 0    💬 0    📌 0

I've made a tool that lets you explore Text Embedding Vectors (an important step for AI tools which use Retrieval Augmented Generation) in a 3D space.

You can choose between different dimension reductions, which helps you compare features.

27.12.2024 17:13 — 👍 2    🔁 0    💬 1    📌 0