I’ve been really impressed with OpenAI embeddings + vector searches for some full document searches compared to something like standard elasticsearch over a large body of text. Something I think I’m personally missing from the ChatGPT/GPT4/LLM conversation with regards to information retrieval is nested/graph hierarchies.
An example from a previous job where we used a hand tooled NLP system was querying for doctors/dentists/optometrists and being able to take something like “dentist near me who is available in the afternoons and speaks spanish”. We would parse this user query into a few different queries that would run against a search cluster and database to return the filtered result set, or the closest output.
What would be the ideal way to prepare or tokenize this data for querying with an LLM? It’s partially text (match dentist, speak Spanish), partially geographic (near me, doing a geo radius of N miles from providers location, and part filtering (who meets all those criteria and has availability in a time frame). Is this a use case for large token sizes to be able to take in all possible providers? Or parsing a query more easily from human language -> SQL/other data store query language? Or perhaps figuring out another way to encode this data?
Two different streams that have built up over time. I spend less than 10 hours combined weekly on them averaged over a month if i had to guess but both were independent full time jobs at one point
1) ($$m total, $$k/mo now) Server hosting! This started off as hosting game servers for friends in early high school. It expanded to friends of friends for awhile before I pivoted more towards crypto mining (yes I know, young kid with dubious ambitions). Lots of my first software experience was here. I wrote some software for switching the processes between mining/game hosting across the different boxes (raw processes on servers, the horror). Nowadays it’s winding down as just game hosting and some scientific computing rental to a few universities/their robotics clubs. It’s still slightly profitable but I have no interest in updating servers (CPUs from 2013-2015, GPUs mostly re-sold except for what a few people requested) and it runs everything via containers now.
2) ($$k/mo) Sports film review. I wrote the first version of this my first year of college which was a way to keep the stats book for basketball and football games and stitch the actions with the video footage. We had customers throughout ~20 states primarily high school but some colleges as well. In fact it still runs at a lot of them, but I’m not really connected with managing of it anymore. My co-founder still runs it and we rotate a few students from our alma-matter in as interns and occasionally juniors on it.
This became the basis for an esports version of the software that I created a few years ago. This time with CV to do all the gathering of stats and allowing for jumping around in videos and analyzing overall stats from the output. This started in Call of Duty for their then new professional league but expanded out to Halo, Rocket League and Valorant since. I still do some occasional retraining of the models but the product itself got acqui-hired by a larger company for which I still “consult”
EDIT: I’ve also had many more that cost me more money than they ever made, but I’m a big proponent of failing fast and iterating
IMO, the release of Warzone 1, Call of Duty’s Battle Royale mode that released a few months after Modern Warfare 2019, has completely changed the priorities and incentives for the company. The goal is to sell in game cosmetics more so than the game itself, as many other games are turning to as well.
The yearly release cycle, which may be ending soon, leads to bugs that re-emerge each year and features that appear and disappear. Sure, the different studios which produce the games need some room to innovate, but the inconsistent base set of features is incredibly frustrating. CoD games are one of the games I play the most, with the other being a game which is the complete opposite, Old School RuneScape, that has been built on for ~20 years.
I play the current game MWII with friends a few hours a day most days of the week. Multiple times per session my game crashes at random, something I can’t remember with any other major games with a top of the line PC. Like many other pieces of software, chasing other revenue sources seems to have made the quality of the product take a nose dive, with consequences yet to be seen. This is disappointing to me as someone who enjoys playing the game with friends, who has competed in open-bracket events at major tournaments over a span of a few years, and worked directly with the professional league and teams (CDL and CWL) for analytics and software.
> The goal is to sell in game cosmetics more so than the game itself, as many other games are turning to as well.
This has nothing to do with cosmetics and everything to do with customer standards. We're living in an age where the average customer has absolutely zero standards for the products they purchase, they simply do not care if the game barely works and crashes every 10 minutes, they will happily enjoy it and praise it anyway because they probably do not have the intellectual capacity to notice or care.
The newest Pokemon game is a prime example of this, it has no cosmetics, no microtransactions, nothing, yet it's so much more of a technical trainwreck than any CoD game, you really have to play it to believe it. It costs $60 and looks and runs worse than many PS2 games, but it sold tens of millions anyway because the people buying it are effectively zombies that only exist to obey corporations and will happily consume whatever is sold to them no questions asked.
What a ridiculous statement to make about people who enjoyed the latest Pokemon games. Yes they perform like ass. Yes they're buggy. But they're still surprisingly fun.
I hated the frame rate issues and various bugs I ran into. I considered requesting a refund (like I did do for similar reasons very quickly after buying Cyberpunk 2077). But before I knew it I was hours into the game. This is actually the first mainline Pokemon game in 15 years that I've played up through the Elite Four on. For me, the fun of the gameplay was enough to outweigh the negatives.
Also, don't forget that even back when games were significantly simpler they were still loaded with issues. The original Pokemon games are a good example here. They had many bugs, some of which were quickly found to be exploitable. To me that's another data point to indicate that issues with the game's coding don't necessarily make the game bad.
> We're living in an age where the average customer has absolutely zero standards for the products they purchase, they simply do not care if the game barely works and crashes every 10 min
Elder Scrolls titles have been selling very well for a long time. I don't think this is new.
Is there a name for the phenomenon of people thinking that some behavior of humans is new when it's actually always been that way? I feel like there should be since it's so common to see the word "nowadays" followed by a statement like that.
Same experience here. I crash/bug-out multiple times per day. Every day I play, the first time I play a map it lags for the first 3-5 minutes, cycling between full speed and 20FPS. I have run into _several_ game breaking bugs in multiplayer, one of which locks me out of playing consistently (detailed in another comment in this thread).
I am big on boycotting and generally have avoided Activision games because of how they have milked things in the past. I'm incredibly frustrated with the state of the game, and disappointed I got talked into buying it by my buddies. Even worse, they just stockholm it saying things like "they just released it, you have to give it time". What? We played Halo 2 and Modern Warfare 2 at launch for a week straight and the only issue I can remember is server instability which was transient. I'm so tired of this public beta workflow, which if you are pushing a game per year you end up getting what, 9 months of _actual_ gameplay, and thats assuming the game doesnt need app-level modifications (vs fixing actual bugs) to smooth out the experience.
I would love to see something akin to an M-based Mac as a dev board of sorts, but I’m fairly sure it would never happen. My home server has transitioned over time from various 4u rack mount options, to a 2u and an M1 Mac Mini, to a Mac Studio with a disk enclosure.
I even tried using a Snapdragon phone dev board for awhile for something more than an RPi
It's a bit annoying that (with the exception of Apple) ARM only exists in the low end and in the high-end cloud server space. There is no ARM equivalent to the Core i5 generally available.
My (non-professional) opinion is that Intel has invested a lot of money into making really good memory and I/O controllers. We need someone to do that in the ARM space as well, which is a really hard-sell. There are no manufacturers out there that want to pay the ARM licensing fee, period. Apple can eat the costs because they sell direct-to-consumer and like to control as much of their stack as possible. Other companies are probably groaning at the thought of fixing all of ARM's problems just so they can be treated as a second-class platform relative to Apple Silicon. Besides Nvidia or Qualcomm, I don't really think there are many companies poised to deliver this, much less an incentive to provide anything.
RISC-V on the other hand, seems like it could be ripe for rapid iteration. We're obviously still in the super-early days of the ISA, but the lack of oppressive licensing has already been a boon for the dozens of hobbyist boards we've seen released in the past few years. As long as Apple doesn't try to EEE the ISA like they're trying to do with ARM, I think the future is pretty bright for open architectures.
The 8cx Gen 3 is better than Qualcomm's other stuff but it's still generations behind a current Core i5. They're about 20% slower than a last-gen Core i5.
I switched jobs recently and became the defacto DevOps person so have been able to deploy mostly how I want. I’ve used kubernetes at multiple jobs, side projects and at home but for a cost and time constrained startup we are leveraging ECS/Lambda/Batch/Cloudfront. B2C application, mostly low traffic with nearly no traffic off hours. Occasionally we’ll get a big rush, 2 to 3 orders of magnitude more traffic than usual, from a marketing push and haven’t ran into any issues yet.
I still run KEDA at home for managing plex, home assistant, some game servers and other of my own projects. But being the only one who is using the cluster is a different use case than getting RBAC, ingress and management set up correctly for a production cluster IMO. I’ve never had the sole responsibility or permission over a cluster before, so it was a daunting step I decided not to take for my own sake
Yes Pokémon Legends: Arceus was a tipping point for me. The game does not look good at all to me, and across 3 different switches I tested, it felt like it was hitching and not loading correctly even with the low detail and resolution in docked mode. I’m handheld it’s a bit better, but that’s not really how I want to play the game.
On the other hand, my most played game is by far Old School RuneScape, which is a restore of a backup of RuneScape from 2007. The game has certainly evolved in style and content since the re-release, and I use a 3rd party client with an “HD” plug-in which adds more render distance, shadows, lighting and anti-aliasing.
Like the others have said, definitely seems to be hit or miss. I inherited an old cluster running on elastic cloud, migrated it to AWS managed and it reduced monthly costs by nearly an order of magnitude on top of going from a 5-15 minute outage per day for master node election to having 3 over 2 years.
We’ve rewritten most of the interactions with the older version of ES into a new service and use a self-managed OpenSearch cluster on Graviton instances and it’s the most stable Elasticsearch/Solr solution I’ve ever interacted with
Poking a bit at the documentation, I see like/ilike but are there plans for text search/trigram capabilities? Recently I’ve been working with lots of different entities that have searchable properties and exploring searching across different elasticsearch indexes to do “JOIN” like operations but have been exploring Postgres (and related) solutions for better “JOIN” support out of the box
Yep, we have plans for that. We are exploring if it would be feasible to make it possible to plug-in external engines like elastic and make that integration totally automatic, enabled with a simple annotation in the schema.
Even better then I would have thought, thanks! I’ve primarily dealt with Elasticsearch/Solr in my career, so jumping into the way searches work in Postgres with various native support and plugins is, interesting to say the least. Maybe I just need to break my Lucene roots
To get around the separate directories/copies someone established a pattern of doing a for each environment at the top of each tf file and then all variables are stored as a map of each env, which I find interesting.
The pattern exists in one repo with the other being all the duplicates, they’ve been in “it just works” for long enough that no one has changed them. Workspaces look pretty slick, I’ll have to check them out
My manager is aware only because we have worked together several times, but he still fights for a yearly raise on the 5-15% scale of things without me asking, and does for other team members as far as I know. For the most part I work 5 by 5s but if there is a meeting or it’s my turn to be the on call engineer I don’t get to shove those duties to the side because they aren’t fun. I have followed and will continue to follow said manager for the foreseeable future due to the relationship we have
An example from a previous job where we used a hand tooled NLP system was querying for doctors/dentists/optometrists and being able to take something like “dentist near me who is available in the afternoons and speaks spanish”. We would parse this user query into a few different queries that would run against a search cluster and database to return the filtered result set, or the closest output.
What would be the ideal way to prepare or tokenize this data for querying with an LLM? It’s partially text (match dentist, speak Spanish), partially geographic (near me, doing a geo radius of N miles from providers location, and part filtering (who meets all those criteria and has availability in a time frame). Is this a use case for large token sizes to be able to take in all possible providers? Or parsing a query more easily from human language -> SQL/other data store query language? Or perhaps figuring out another way to encode this data?