Perhaps it was John Koza?
1,001 karma · joined September 20, 2013
mail me at github at hella dot rip
I gave it a shot for a few months and it was useful to go back to catch things that I couldn't quite recall. It was handy to ask it things instead of doing direct search sometimes. It was helpful for work, where I tend to take notes on things but never review them because of their volume (and SNR). I wound up uninstalling it because it was not the 'superpower' they alluded to in the marketing material, but it was interesting nonetheless. I also whipped up my own version using Ollama to provide access to a decent LLM (Command-R) on my LAN, recording screenshots, text, and transcripts to LanceDB so I could do combined search by vector and keyword and then re-rank. Also a fun project to learn from, but not that useful in the end.
> Arthur Lee, “Mr. Podunkian” (1.4 & 1.5 updates), Tom Coxon (Multiplayer net code in 1.3), Alex Erlandson, “Zillix” (1.4 update), Sickhead Games (Console ports), The Secret Police (Mobile ports)
(full credits can be found in the game’s title screen)
Ref: http://www.sciencedirect.com/science/article/pii/03043975940...
It's up to the app to put that into the context. Generally, coding LLMs do well if you provide them the source tree, graph, search results, notable files, etc in the context. The is how Sourcegraph's Cody product works, for example.
What do you make of TFA in this case? Does it erode that trust or would you go the same route again?
I think many of us have been waiting in the wings and need to be seriously impressed before donning a headset regularly. My internal resistance stems from both comfort and ease of operating it for general compute outside of games. I have a Valve Index and have had some delightful experiences with it, but there's a big gap to jump into "routine" daily driver territory in my mind.
With a couple quick attempts, it completely changed all of my 8 jobs over 20 years to include mentions of the target job, even if it meant adding unbelievable lies like running a scuba certification program and improving training using my knowledge of library sciences. The instructions may need examples of how to remain truthful and to just skip roles that are hopelessly unrelated instead of fabrication.
You could even suggest it adopt a multi-step process with a self-evaluation if that helps. I made a recipe reformatter that worked that way and it improved the output by finding places it accidentally dropped or changed an ingredient's amount, for example.
> A batch of proposed class actions filed in Washington state against major companies such as adidas AG, Home Depot Inc., and Marriott International Inc., will help employers gauge the litigation risk they face under a recent nationwide wave of pay transparency laws requiring salary ranges in job ads.
The wheels are starting to turn. I think there are more class actions happening than individual cases but IANAL.
https://news.bloomberglaw.com/daily-labor-report/adidas-home...
https://github.com/JaidedAI/EasyOCR#whats-coming-next
Happy to see OCR is advancing lately, but I really need HWR.
I am looking for something this polished and reliable for handwriting, does anyone have any pointers? I want to integrate it in a workflow with my eink tablet I take notes on. A few years ago, I tried various models, but they performed poorly (around 80% accuracy) on my handwriting, which I can read almost 90% of the time.
> AlphaTensor discovered algorithms that outperform the state-of-the-art complexity for many matrix sizes. Particularly relevant is the case of 4 × 4 matrices in a finite field, where AlphaTensor’s algorithm improves on Strassen’s two-level algorithm for the first time, to our knowledge, since its discovery 50 years ago.
https://towardsdatascience.com/how-deepmind-discovered-new-w...
https://www.nps.gov/parkhistory/online_books/olym/schalk/cha...
> In comparing the various palynological sources for Northwestern Washington and surrounding regions, it is clear that the vegetation history varies at least in its details from area to area. For example, Heusser (1978:1576) notes that treeless conditions persisted longer after glacial retreat in the Hoh Valley than in the northwestern corner of the Olympic Peninsula.
> ...the arrival of coniferous trees in this area was apparently delayed by aridity until sometime between 11,000 and 9,600 yr B.P.