Making AI work for your Confluence knowledge base
New York, USA
Joined January 2013
- Tweets279
- Following243
- Followers172
- Likes396
Human in the loop (prefer bursts, frustrated by 5h limits when in the zone) vs autonomous agents (and token resellers perhaps).
I should have used the word consistency instead of reproducibility. E,g, different models may require adjustments to prompts/skills to perform their best. Better overall may be worse in particular scenarios. Losing the model one has invested in may require painful adaptation.
This makes difficult using DS in scenarios where reproducibility is important: agents doing e.g. automated checks. Since you decide what better is, users will need to periodically retest their workflows or be left behind. Not bad, just limits use cases which is a fair UX choice.
More precisely, it implements an efficient LLM token selector driven by a JSON schema, with application examples on MLX. This is better that GNBF in that mapping to GNBF can produce unwieldy rule sets for things like min and max number of items in an array . @awnihannun @simonw
Check out this repo Simon, it implements json schema on mlx github.com/otriscon/llm-stru…
For Mac (MLX) there’s github.com/otriscon/llm-stru… which works with any model.
✅ Against GPT-3.5-Turbo, we saw a 17% reduction in hallucination and similarly improved recall, at a 10x cost and 2x latency.
blog.alu.ai/evaluating-gpt-4…
We evaluated GPT-4-Turbo in our pipeline and found it a very useful addition to the palette of LLMs available, although not a complete game-changer.
✅ Against GPT-4, we saw 66% reduction in latency and cost with an estimated 5% decrease in quality (F1 score).
(1/2)
Of course, to write the story for the submission, we enlisted AI help.
blog.alu.ai/participating-in…
What’s the point of AI if you can’t rely on its output? We are building a trustworthy assistant for Confluence that tells you exactly how it got its answers. Not just sources, but every reasoning step. Read more in our blog: blog.alu.ai/introducing-x-ra…
Atlassian has just released the public beta of Atlassian Intelligence. We had a first look and found it still has some way to go before being trustworthy. Link to our report below.
Connie AI can now answer sophisticated questions about tabular data. We translate natural language queries to a pseudo-SQL language and execute it over your Confluence tables. Support for the new Confluence Databases coming soon.
New post in our blog: streaming OpenAI function calls. blog.alu.ai/streaming-openai…
Connie AI (connie.alu.ai). We’re ex-Atlassians building an AI assistant for Confluence. It’s miles ahead of Confluence search already.