I think they'll keep the status quo of quarterly, bc if any announce switching I'd expect their stock value to fall (bc in my mind the decision would transmit more bad potential than positive potential for future earnings). ie- I don't buy that quarterly reporting drives too short-term decision-making (or that it's generally too short).
I built this after noticing how much variation there is in AI output depending on the quality of the prompt. Models matter a lot — but even the best model underperforms when the prompt is vague. Enriching the input is one of the highest-leverage things you can do.
Most prompts are drafted in 10 seconds and sent. They're missing context, constraints, a clear objective, examples. The model fills in the gaps with whatever it wants, which is why the output often feels generic or off.
Prompt Enricher scores your prompt across 5 dimensions (the YIELD framework: Your Objective, Input Context, Expectations & Constraints, Layout of Output, Demonstrations/Examples), then rewrites it with the missing pieces filled in. It also produces 4 variants — Packed, Quality, Concise, and Reliable — so you can match the enriched prompt to your use case.
The "Show Changes" diff view that highlights exactly what was added (green) and removed (red) — so it's immediately clear what enrichment actually did to your prompt.
Unfortunately they're still too superficial. 9 times out of 10 they don't have enough context to properly implement something and end up just tacking it on in some random place with no regard for the bigger architecture. Even if you do tell it something in an AGENT.md file or something, it often just doesn't follow it.
Seems false. The Atlantic Monthly, to take an example --- another publication I subscribe to --- is an order of magnitude smaller than the Post. If the Post wanted to run the Atlantic's business successfully, they could; they'd just have to lay almost everybody else in the company off.
That the Post's predicament is a consequence of Bezos partisan editorial decisions. I don't like those decisions either, but I don't think they get close to the core problem the Post faces.
Indeed. It's really, really something when I can even entertain the idea of 'I'll go to Wal-Mart, it's awful but at least it's a lot morally better than supporting Amazon'. Yikes!
It’s possible to run up to 4 agents at once vs. Claude Code’s single thread. Sometimes I’ll find meaningful quality differences between what agents produce.
That reminds me of when teachers would say: what if you're without a calculator? And yet we all have smartphones in our pockets today with calculators.
> That reminds me of when teachers would say: what if you're without a calculator? And yet we all have smartphones in our pockets today with calculators.
Your teachers had the right goal, but a bad argument. Learning arithmetic isn't just about being able to do a calculation. It's about getting your brain comfortable with math. If you always have to pull out a goddamn calculator, you'll be extremely limited.
Trust me, elementary-age me was dumb to not listen to those teachers and to become so calculator-dependent.
I think learning arithmetic is a good idea, but it’s only a part of computation. I don’t think we should get too hung up on a particular method of computation (bc there’s so many ways).
Very fair. I think even more we underestimate our own sentimentalities. eg- the teacher that believes adding or multiplication has to be done a particular way (like the standard algorithm vs. partial products).
Having a deep intuition about what the calculator is doing is the skill we were actually being taught. Teachers don't know always understand why things are being taught.
> Teachers don't know always understand why things are being taught.
Yes, but I don't think that is the actual bottleneck, even when they do, most children probably don't care about abstract goals, but rather about immediate skills in their everyday life, or just the statement, that they will need it.
I guess I'm just trying to suggest that teachers sometimes might think they know why things are being taught, and make claims like "you wont always have a calculator" as the reason for learning mathematics.
One conclusion might be that it'd be better for some students if teachers understood the why, as they might change their approach on some subjects. An example: knowing that certain equations and patterns EXIST, and which kinds of problems they apply to, is generally much more important that knowing the actual equations by heart themselves.
And yet calculating your shopping expenses to prevent getting screwed by buggy vending machines, or quickly making rough estimations at your work, is as useful as ever. Tell me how you can learn calculus and group theory, when you skipped primary school math.
This link https://wismuth.com/chess/longest-game.html from the article talks about the 2014 changes (75-move rule and draw by 5-fold repetition) that make it no longer infinite.
That was also my intuition. Unless there's a rule that can stop two immortal but dumb-as-bricks players from indefinitely cycling through the same non-capturing moves surely the answer is 'infinity'.
It depends what rules you're using, but there are the three-fold repetition and 50-move rules which allow a player to force the game to end in a draw. The catch is they both require one of the players to claim a draw under the rule, otherwise they can keep playing.
There is additionally the 75-move rule where the the game is forced to be over without either player claiming the rule (the arbiter just ends the game), that rule would give an upper bound regardless of the players knowledge of the rules.
As I understand it, the 50-move rule must be invoked by one of the players, lets assume our immortal players agree not to invoke that rule.
The 75-move rule is automatic, so that would be the limiting factor.
Note, that 75-move rule is only applicable after no pawn has moved or a piece has been captured. So our immortals can do a lot of shuffling things around.
I'm thinking that the number of moves of the longest game is going to be (16 pawns * 7 moves each + 16 pawns being captured + 14 other pieces each being captured, not the kings) * 75 moves for shuffling around = 10650 moves.
That's only 1 week at 1 move per minute! But given the permutations, it might take much longer to calculate the actual moves required to get to the end state :)
Pawns only get 6 moves :) But also they can't all make 6 moves because they can only move past each-other via capture, so half of them would get 5 moves instead (if you're counting all the captures), so that gives a maximum of ~8850.
How I'd put it is that there are two sets of stopping points under FIDE rules:
- After threefold repetition or 50 moves, either player may claim a draw.
- After fivefold repetition or 75 moves, the game is automatically drawn.
Most modern counts of the longest possible chess game, or the total number of possible chess games, are based on fivefold repetition and the 75-move rule.
Meanwhile, threefold repetition and the 50-move rule are still relevant in endgame tablebases, since they rule out certain forced mate sequences.
Endgame tablebases don't take into account threefold repetition; if so, you would have to basically be able to exclude any arbitrary position from the tree, which would seem impossible. The 50-move rule is respected by the Syzygy tablebases, though with the concession that they do not generally give the fewest possible moves to mate (they would rather delay the mate than delaying a pawn push or a capture).
Here's an example (adapted from the URL below): https://syzygy-tables.info/?fen=3R4/5R2/8/8/8/1K6/8/4k3_w_-_... — if you asked pretty much any player, even a child, how to win this, they'd show the staircase mate starting with Re7+ (mate in 4). If you asked a computer or the older Nalimov tablebases, it would say Kc2! (mate in 2). However, if you ask the Syzygy tablebases, they would argue that this is not optimal if we are extremely close to the 50-move rule, so the safest and thus best move is Rf2!! which forces Black to capture the rook on the next turn (they have no other legal moves), resetting the counter and giving a mate in 18.
There were a set of experimental DTM50 tablebases made at some point (though not made public); they store the shortest mate for all 100 possible zeroing counters in any position. See https://galen.xyz/egtb50/ for some discussion.
reply