Nolt Reviews

Jsonformer Reviews

Nolt mentions (7)

• Rust future

  Seems like nolt.io and rust feedback is privated at the moment, must have had ppl bombing it after the update. Source: 12 months ago

• So I just built an Upvote board application inspired by 50hacks

  - Employee feedback board - a place where bigger companies can head their employees and their problems (https://nolt.io/ for employees and companies). Source: almost 2 years ago

• stop getting pissed at losing

  Well it is one of the better early tier monuments, what other reason would they have for making it easier? It has always worked properly and fine. Also there was a MASSIVE uproar from the community because of it, if it wasnt just for the noobs they would have left it. https://rust.nolt.io/ had practically nothing but complaints from players on it for weeks, to this day I still occasionally see it. Not to mention... Source: about 2 years ago

• Bigscreen roadmap, most voted ideas, user suggestions?

  If anyone at bigscreen reading this then please make a http://feedback.bigscreenvr.com/ page and use Nolt · Feedback boards your users will love or something like this or make a custom one, so anyone can see your roadmap and give suggestion and vote ideas. It will also help you to know what users want and you will also get lot of free ideas. Source: over 2 years ago

• If you could create a bedwars kit, what would it be?

  I actually did make a kit idea once and put it on the nolt.io page let me get it rq. Source: over 2 years ago

Jsonformer mentions (9)

• Show HN: LLMs can generate valid JSON 100% of the time

  How does this compare in terms of latency, cost, and effectiveness to jsonformer? https://github.com/1rgs/jsonformer. - Source: Hacker News / 10 months ago

• Show HN: LLMs can generate valid JSON 100% of the time

  I'm not sure how this is different than: https://github.com/1rgs/jsonformer or https://github.com/mkuchnik/relm or https://github.com/Shopify/torch-grammar Overall there are a ton of these logit based guidance systems, the reason they don't get tons of traction is the SOTA models are behind REST APIs that don't enable this fine-grained approach. Those... - Source: Hacker News / 10 months ago

• Ask HN: Explain how size of input changes ChatGPT performance

  You're correct with interpreting how the model works wrt it returning tokens one at a time. The model returns one token, and the entire context window gets shifted right by one to for account it when generating the next one. As for model performance at different context sizes, it's seems a bit complicated. From what I understand, even if models are tweaked (for example using the superHOT RoPE hack or sparse... - Source: Hacker News / 11 months ago

• LLMs for Schema Augmentation

  From here, we just need to continue generating tokens until we get to a closing quote. This approach was borrowed from Jsonformer which uses a similar approach to induce LLMs to generate structured output. Continuing to do so for each property using Replit's code LLM gives the following output:. - Source: dev.to / 11 months ago

• Doesn't a 4090 massively overpower a 3090 for running local LLMs?

  Https://github.com/1rgs/jsonformer or https://github.com/microsoft/guidance may help get better results, but I ended up with a bit more of a custom solution. Source: 12 months ago