fryz

looks like the white king/queen aren't on the right colors (queen goes on her color) - confused me a bit when trying to map the space to a 2d board

The "magic" is done via the JSON schemas that are passed in along with the definition of the tool.

Structured Output APIs (inc. the Tool API) take the schema and build a Context-free Grammar, which is then used during generation to mask which tokens can be output.

I found https://openai.com/index/introducing-structured-outputs-in-t... (have to scroll down a bit to the "under the hood" section) and https://www.leewayhertz.com/structured-outputs-in-llms/#cons... to be pretty good resources

yeah - it's one of the best success stories of wildlife conservation in the modern era.

FWIW, not saying it's right (as a hunter I wouldn't ever do this myself), but most of the biologists that build the population models, inc. the ones that they use to set the amount of hunting licenses or tags sold, build a certain amount of poaching into their models.

It's a particularly hard problem to solve - the hobby is usually spread through traditional means (you do it if your parents did it), and going all the way back in certain communities this was the main way to get meat, even before it became regulated. It's difficult to stop something that not only puts food on the table for your family, but has been done that way for generations.

This was one of the main contributors to the decline of the turkey population in the lower 48. In the early 1900's, a lot of folks thought turkey's were extinct because of over hunting and poaching, and the National Wild Turkey Foundation took efforts to restore the population for hunting.

This is one of those joyful concepts you learn about as a homeowner, especially on older homes.

If you have plumbing that's done in different metal materials (copper, steel, lead, etc.) and any of your pipes touch, you have to perform regular maintenance and apply a dielectric grease (another one of those single-use materials that you have to buy and store away) or your pipes could corrode and cause a ton of damage.

Yeah thanks for the feedback.

We think we stand out from our competitors in the space because we built first for the enterprise case, with consideration for things like data governance, acceptable use, and data privacy and information security that can be deployed in managed easily and reliably in customer-managed environments.

A lot of the products today have similar evaluations and metrics, but they either offer a SAAS solution or require some onerous integration into your application stack.

Because we started w/ the enterprise first, our goal was to get to value as quickly and as easily as possible (to avoid shoulder-surfing over zoom calls because we don't have access to the service), and think this plays out well with our product.

Yeah great question

We based our hallucination detection on "groundedness" on a claim-by-claim basis, which evaluates whether the LLM response can be cited in provided context (eg: message history, tool calls, retrieved context from a vector DB, etc.)

We split the response into multiple claims, determine if a claim needs to be evaluated (eg: and isn't just some boilerplate) and then check to see if the claim is referenced in the context.

You're not wrong but suffering isn't comparative. Because it's easier for someone to bounce back or have support in the transition doesn't mean it still doesn't suck.

To add some color to this

Anthropic does a good job of breaking down some common architecture around using these components [1] (good outline of this if you prefer video [2]).

"Agent" is definitely an overloaded term - the best framing of this I've seen is aligns more closely with the Anthropic definition. Specifically, an "agent" is a GenAI system that dynamically identifies the tasks ("steps" from the parent comment) without having to be instructed that those are the steps. There are obvious parallels to the reasoning capabilities that we've seen released in the latest cut of the foundation models.

So for example, the "Agent" would first build a plan for how to address the query, dynamically farm out the steps in that plan to other LLM calls, and then evaluate execution for correctness/success.

[1] https://www.anthropic.com/research/building-effective-agents [2] https://www.youtube.com/watch?v=pGdZ2SnrKFU

Neat article - I know the author mentioned this in the post, but I only see this working as long as a few assumptions hold:

* avg tenure / skill level of team is relatively uniform

* team is small with high-touch comms (eg: same/near timezone)

* most importantly - everyone feels accountable and has agency for work others do (eg: codebase is small, relatively simple, etc)

Where I would expect to see this fall apart is when these assumptions drift and holding accountability becomes harder. When folks start to specialize, something becomes complex, or work quality is sacrificed for short-term deliverables, the folks that feel the pain are the defense folks and they dont have agency to drive the improvements.

The incentives for folks on defense are completely different than folks on offense, which can make conversations about what to prioritize difficult in the long term.

shhhhhh - dont give it up :)

Part of whats nice about it is that there isnt a ton of people and the NJ stereotypes work out in our favor.

FWIW, I find the classical chess tournaments with the super GMs to be fairly interesting, if only because the focus of the games is more about the metagame than about the game itself.

The article linked at the bottom of the source is a WSJ piece about how Magnus beats the best players because of the "human element".

A lot about the games today are about opening preparation, where the goal is to out-prepare and surprise your opponent by studying opening lines and esoteric responses (somewhere computer play has drastically opened up new fields). Similarly, during the middle/end-games, the best players will try to force uncomfortable decisions on their opponents, knowing what positions their opponents tend to not prefer. For example, in the candidates game round 1, Fabiano took Hikari into a position that had very little in the way of aggressive counter-play, effectively taking away a big advantage that Hikaru would otherwise have had.

Watching these games feels somewhat akin to watching generals develop strategies trying to out maneuver their counterparts on the other side, taking into consideration their strengths and weaknesses as much as the tactics/deployment of troops/etc.

From the article:

When I asked Jody how much of his family’s meat is wild game, he initially said “about half.” Upon reflection, he bumped the number to 70 percent.

Doesn't sound like this is a justification for "culture" or "tradition". Certainly seems a lot more responsible than the average "tradition" of "I got it at the grocery store".

When you hunt for your own food, you are forced to consider the sacrifice of the animal and have to put in the work of preparing for the hunt and cleaning the animal. Things that anyone who's not done this takes for granted when they eat meat.

Maybe we've not gotten there yet (kids are 2 and 1), but they can watch the same thing thousands of times and it will still glue them to the TV.

You might not be the right market (or at least, the marketplace might be different for your demographic).

I'm a parent, and for me, and all my parent friends, Disney+ is the streaming service that generates the most value in our households. Along with all the old/nostalgic Disney animated films, they generate and acquire a lot of the "in" content for kids (Bluey, Mickey Mouse Kids House, etc.)

Before my kids, Disney+ would have been the first streaming service to make the cut. But now, it'll be the last.

Yeah - and it wasn't even necessarily on the tech stuff either - the talks are definitely the things that have stuck with me the longest after working there (and it's been 10+ years!)

Haven't seen anyone mention a non-DOE lab, so figured I'd weigh in.

I interned twice with MIT Lincoln Labs, which among other things, helped build and deploy Radar for WWII which turned into building/managing the technology for Air-Traffic Control, and then turned towards space.

They are primarily a DOD-associated research lab (even located on an US Air Force Base), and so most of the projects have some military-oriented mission. Their mission is entrepreneurial-minded (which I found cool), in that they do the "basic research" and prototyping to prove viability and then the DOD turns over the project to a contractor to make feasible.

While I was there I worked in their GeoIntelligence and Natural Language groups, doing research which I'd ultimately come to understand as being relevant for Project Maven (year 1) and PRISM (year 2). While I'm sure as an intern my contributions weren't directly related to or otherwise leveraged for these programs, in hindsight it was clear that this was the bigger picture that the work was contributing to. Take from this what you will.

Most of the anecdotes that I've read through in the comments mirrors my experience. However, one thing I see missing was how opportunity was "metered" out. Each group I was in was organized like a research lab and the level of your academic progression limited (or opened) your ability to get access to specific projects/work. Their pay scale was also dictated based on this as well. So if you have a BS, your ability to "move up", doesn't exist, but it does if you have PhD.

Ultimately, I was given an offer to work there, but ended up taking a SWE position in the Bay Area because I wasn't interested in continuing my education and felt like my ability to have a career progression at MITLL would have necessitated that.

It's cool to see some commentary regarding how hunters and federal policy helped (and hurt).

The National Wild Turkey Foundation is solely responsible for the reintroduction of the turkey across most of the entire US. The entire purpose of the mission was to bring wild turkey populations up for hunting, and that hunters would be the best way to conserve and manage the population.

An excellent podcast done by Steve Rinella (another hunter/conservationist, famous for his Meat Eater TV Show) about the topic: https://www.themeateater.com/listen/meateater/ep-104-turks.

From the episode: the way the NWTF and DOW people captured Wild Turkeys was to design a gun that could shoot webs, capture the turkeys, throw them into a van, and drive them out and drop them off in the woods in another state.