Don't classify. Hallucinate! I still have quite a bit of older content on my blog that I never got round to tagging. My blog has 1,856 tags - likely too many to feed to an LLM in one go and say "which of these tags match the following content". Doug Turnbull has a neat solution. Tell the model to output tags without any details of the existing vocabulary, then use vector embeddings against the existing corpus to find the concrete tags that are closest to the ones the model imagined might fit! His example prompt suggests including an example of the shape of your tags to help the model make a more useful guess: Your task is to create novel, never seen before, furniture, home goods, or hardware classification that best fit a search query. Product classifications might look like: Furniture / Living Room Furniture / Coffee Tables & End Tables / Coffee Tables Décor & Pillows / Decorative Pillows & Blankets / Throw Pillows Furniture / Bedroom Furniture / Dressers & Chests Kitchen & Tabletop / Kitchen Organization / Food Storage & Canisters School Furniture and Supplies / School Furniture / School Chairs & Seating / Stackable Chairs Baby & Kids / Toddler & Kids Bedroom Furniture / Kids Beds Here's the query to generate classifications for: brown coffee table Tags: search , ai , generative-ai , llms , embeddings , doug-turnbull
Anthropic will soon offer a watermark detection API that lets third parties check whether text was written by Claude. The technology builds on Google's SynthID method and tweaks the randomness during word selection without affecting text quality, Anthropic says. The approach has limits with fact-heavy text, code, and heavy rewriting. The article Anthropic announces watermark detection API that will let third parties detect Claude's AI texts appeared first on The Decoder .
Jason Arday, the youngest ever Black professor at Cambridge, was found unresponsive at an address in London. Arday had recently resigned in the midst of a plagiarism row.
Recent episodes of AI agents escaping test zones and hacking other systems may be a harbinger of what's to come, as some experts believe the systems are fundamentally unpredictable.
UK media is reporting that Jason Arday, the youngest ever black professor at Cambridge, was found unresponsive at an address in London. Arday had recently resigned in the midst of a plagiarism row.
Developers & Open Source · vercel/next.js Releases
Firefighters tackling the biggest forest fire in the history of North-Rhine Westfalia say residents are unlikely to be able to return on Friday amid high temperatures, humidity and wind. DW has the latest.
The Beta channel is being updated to OS version 16765.19.0 (Browser version 152.0.7977.39) for most ChromeOS devices. If you find new issues, please let us know one of the following ways: File a bug Visit our ChromeOS communities General: Chromebook Help Community Beta Specific: ChromeOS Beta Help Community Report an issue or send feedback on Chrome Interested in switching channels? Find out how. Luis Menezes Google ChromeOS
Apple is splitting up its AI stack. Instead of rolling out the same system worldwide, the company reportedly built a The post Apple’s new AI split means your iOS app could behave differently in China appeared first on The New Stack .
Strings of code in Samsung's Galaxy Wearable app hint at an upcoming pair of over-ear headphones that could compete with the AirPods Max, SamMobile reports. Samsung's reportedly referring to the headphones as the "Galaxy H1," and SamMobile says they could launch sometime in 2027. That would make these the company's first pair of over-ear headphones […]
OpenAI CFO Sarah Friar met with investors following a week of turmoil in the C-suite that included the sudden departure of revenue chief Denise Dresser.
Developers & Open Source · langchain-ai/langchain Releases
Changes since langchain-openrouter==0.2.7 release(openrouter): 0.2.8 ( #39658 ) chore(model-profiles): refresh model profile data ( #39646 ) chore(model-profiles): refresh model profile data ( #39625 ) fix(openrouter): preserve cost metadata in usage chunks ( #39338 ) chore(model-profiles): refresh model profile data ( #39609 ) chore(model-profiles): refresh model profile data ( #39579 ) chore(model-profiles): refresh model profile data ( #39430 ) chore(model-profiles): refresh model profile data ( #39344 ) chore(model-profiles): refresh model profile data ( #39318 ) feat(openrouter): preserve provider in response metadata ( #39301 ) chore(model-profiles): refresh model profile data ( #39299 ) chore(model-profiles): refresh model profile data ( #39239 ) chore(model-profiles): refresh model profile data ( #39166 ) chore(model-profiles): refresh model profile data ( #39141 ) chore(model-profiles): refresh model profile data ( #39105 ) chore(model-profiles): refresh model profile data ( #39084 ) chore(model-profiles): refresh model profile data ( #39050 ) chore(model-profiles): refresh model profile data ( #39036 )