HackerTrans
TopNewTrendsCommentsPastAskShowJobs

simonbutt

no profile record

Submissions

Evaluating Multimodal LLMs Using the Google IO 2024 Puzzle

hiresynth.ai
3 points·by simonbutt·2 tahun yang lalu·2 comments

Am I using it wrong or has the ChatGPT Bing plugin degraded?

chat.openai.com
1 points·by simonbutt·3 tahun yang lalu·1 comments

comments

simonbutt
·2 tahun yang lalu·discuss
A couple weeks ago I rebuilt the https://hiresynth.ai landing page and docs using vitepress and was super impressed with the speed of implementation and how pretty it was by default.

Would recommend for any text heavy static site.
simonbutt
·2 tahun yang lalu·discuss
While opensource models allow you to explore wider topics, I wonder how well mixtral holds context on longer exchanges?
simonbutt
·2 tahun yang lalu·discuss
Wrote a post on multimodal LLMs (GPT-4V, Gemini Ultra, Claude3 Opus) attempting the puzzles at https://hiresynth.ai/blog/googleio_puzzle_multimodal_eval.ht.... Seems very easy for humans, far harder for LLMs currently
simonbutt
·2 tahun yang lalu·discuss
GPT-4V, Claude 3 Opus and Gemini Ultra go head to head in solving GoogleIO Puzzle 2024
simonbutt
·3 tahun yang lalu·discuss
This feels like the start of a lawsuit. If Tesla is state of the art and requires 5x less funding per charger than competition; what is the reasoning behind picking the competitors?
simonbutt
·3 tahun yang lalu·discuss
This feels as if they've tacked the bing "chat with gpt4" to chatgpt while the previous version was able to browse multiple places and provide (usually) decent responses.

Have you found any custom instructions to improve the way it browses and responds?
simonbutt
·3 tahun yang lalu·discuss
Once in a while HN provides absolute gems. Would never have known about this anti procrastination feature otherwise!
simonbutt
·3 tahun yang lalu·discuss
Logic for azure chatgpt's "infinite context" summarisation is in https://github.com/microsoft/azurechatgpt/blob/main/src/feat...

*Edit Azure chatgpt, would be amazed/disappointed if chatgpt used langchain.