Viewing profile — oli5679

Would llms be more robust to this prompt injection if the tags used in fine tuning are sanitised from user input? E.g. map -> THINK -> USER -> TOOL If they learn something specific…

https://github.com/mistralai/mistral-vibe This is a really nice open source coding agent implementation. The use of async is interesting.

This ties directly into the superposition theory. It is believed dense models cram many features into shared weights, making circuits hard to interpret. Sparsity reduces that press…

The OpenAI fine-tuning api is pretty good - you need to label an evaluation benchmark anyway to systematically iterate on prompts and context, and it’s often creates good results i…

One interesting anecdote about this bill was that the European Commission allegedly funded digital advertisements promoting it, targeting specific political demographics, which is …

HHI is a pretty interesting metric. It’s calculated by taking each firm’s market share, squaring it, and summing across all firms. This gives the probability that two randomly chos…

Here is gpt 5 thinking posting all 20 questions verbatim. Appreciate I might get better results one question at a time. https://chatgpt.com/share/6897a21b-25c0-8011-a10a-85850870da…

It’s really easy to be cynical. There is a big upside potential for high growth companies taking advantage of technology trends. Today, Google’s revenue is £263.66 Billion. This is…

this is pretty ridiculous A. below is a list of OpenAI initial hires from Google. It's implausible to me that there wasn't quite significant transfer of Google IP B. google publish…

I think this project is awesome and am quite disappointed with some cynical commentary from large American labs. Researcher at Meta or OpenAI spending hundreds of millions on compu…

Lendable | Data Science & Software Engineering |Hybrid & Remote | UK, London | Full Time Lendable have built the big three consumer finance products from scratch: loans, credit car…