kuboble

Yes, I have one instance of it per project. And there run only one claude code session that is only supposed to manage "jiraude" and run the actual work in subagents. I published it at https://github.com/kuba97531/jiraude

These days paint has copilot...

> I do not like terminal tui much as I think it's a poor fit for a coding agent

I recently moved away from using tui to directly interact with claude code.

I still start a session in the terminal but then ask to start a simple jira- like ticketing system.

When I have a request I start a new ticket and claude decides to either do it or launch a sub agent to do it.

When claude is done or has questions- he replies in the ticket. When claude has a side-findings he creates a new ticket for me.

For daily chat gemini is great.

actually even gemma locally is great for a lot of chat purposes.

Before the AI first level support often wasn't allowed to type answers but instead copy paste one of the answers from the faq, which was extremely frustrating.

The chat would go like this:

- I have a question about "no vehicles in the park" policy. Does it include motorized wheelchairs?

- To guarantee safety and blablabla our policy is that no vehicles are allowed in the park.

- so can i go to the park with a wheelchair with a battery and electric engine?

- To guarantee safety and blablabla our policy is that no vehicles are allowed in the park. Please see our safety policy (link).

I think people arent more greedy. the problem is more that people can now do harmful things to a lot of other people who arent their direct peers.

This is the exact reason I stopped using claude for chatting. Few times I hit the claude code limits I was unable to ask the simplest question in a chat.

The same way as we protect those anti-internet or anti-electricity ?

To complement on other comments that have already provided definitions.

The big O notation is very often used to denote exact complexity of an algorithm even if the notation is technically an upper bound.

The little o notation is usually used to denote a small asymptotic improvement over some known complexity.

For example if some sublinear algorithm would have n^(7/8) complexity - would be probably advertised as big O of that. But n^(1-eps) is shared as o(n) with exact constant provided as a detail.

I would argue that math indeed makes our lives better. Llms themselves are math invention! It doesn't matter much where this math comes from.

I think it's ok to care about math as an art or sport still.

Math will join the ranks of other useful works where human effort was once essential like

Long distance messaging/ running, painting, calligraphy, weight lifting and others.

But arguably - it's better for chess community that the best engines are opensource than having superior GoogleChessBot.

It has utility so some people will pursue it, but it has no immediate business value so I don't believe ai labs will keep spending millions on it.

Unless they decide that trying p!=np is worth any money.

I wonder if top labs will soon abandon math progress like they did go and chess.

In example of go where I'm more familiar Google deep mind poured large resources to get a super human performance first, establish superiority and abandon it. The community then built their own tools starting from reproducing their papers.

I think similar thing might happen to math. Nobody outside of math cares too much about Hamiltonian cycles in some bizarre graphs or proving lower bounds on complexity of some problem.

Once those results stop being worthy of mainstream media attention, they will abandon math and the progress will be done by mathemicians guiding the models and the community will likely establish some new rules about what makes a valuable contribution. Merely solving not yet solved problem might not be it anymore.

Given the popularity of the benchmark, is there already a human artist scene that outcompetes llms here?

I'm an ok chess player (roughly OP level) and slightly more experienced claude code user.

I tried to use claude to analyze my games using stockfish - this is not a problem claude is good at.

I spent few hours (however admittedly around opus 4.8) with claude on this and it was unable to use stockfish in any useful way.

I think if the skill created by OP works then it's a real contribution. I'll give it a try.

it's the opposite actually.

If someone holds their camera or a phone facing you directly you can guess they are filming you.

Normally looking glasses with a hidden camera is a Spywear from spy novels. The diode doesn't change much

Retiring is to stop doing what other people tell you to do for money.

There is plenty of room for intellectual and social engagement outside of paid work.

I don't know if it's legally binding but hope it is.

I love the saying "you can delegate authority but you can never delegate responsibility".

Your agent committed a crime in your behalf? You're responsible.

I have no logs and exact settings used anymore unfortunately.

One example move was 48. g4 from this game: https://lichess.org/osSoJGzO#95

It's not public, but the diff is tiny: https://pastebin.com/Nd2sS0KX

Also - it's not only my change is making stockfish not blunder. Any little change in the code or execution will butterly-effect into no blunder.

To reproduce a bunder you have to be very deterministic. You need to specify threads = 1, and fixed cache sizes.

N=1 and might be a raw skill issue on my end.

But I all but stopped writing code 13 months ago. At the beginning the code was often bad.

In the last 6 months alone I had received more praise from my customers for excellent work than ever before.

I believe this is not the case. The first reason is the optimization of the Transposition Table in stockfish. https://github.com/official-stockfish/Stockfish/blob/master/...

Basically this optimization means that stockfish will sometimes take a bad read from a cache (so it will take an evaluation of the position from cache which was calculated for a different position). It's fairly random when this will trigger a bad play, but if you brute force vs any deterministic setup you will find it eventually.

But even withtout it - you can just implement a kind of a brute-force heap of positions using stockfish's own eval and you can find wins from almost any position even on fairly high playout count.

I got as far as 32M from different even starting positions, but I spent compute to find as many games as possible rather than as deep as possible.

Example game: https://lichess.org/XVUjezMr#134

the collection of the games I found (vibecoded gui) https://kuboble.com/chess_ideas/

Evaluation doesn't matter as far as I understand. If 19 beats 18 in a match on billion playouts then it's a feature.

Any usability of stockfish evaluation for human analysis is collateral.

Unfortunately there seem to be no serious fork of stockfish that would care about usability for human analysis.

I was recently doing some larger study and I stumbled upon a bug/feature of stockfish where it accepts small number of invalid cache reads for a lot of speed.

It would result in infrequent blunders which however affected my analysis, so I removed this optimization in my fork.

Welp... I bought recently a projector.

It wouldn't start in a dumb mode without first establishing internet connection and a Google account.

The matter didn't have goals, but it randomly (?) Came up with self-replicators and eventually here we are.

if we create a billion agents with the ability to change is own code - through similar evolution we will get agents that do want to survive and are great at self replication.

"Hey Q86, do you want to live?" "I couldn't care less, I'm an LLM" "Don't mind if I take over your hardware then?"

I'm 2 dan.

For a double digit kyu there are two simple things than can give you 2-3 stones boost overnight if you understand them.

- don't play aji keshi.

- endgame starts earlier than you think. If nothing is urgent, play the largest endgame in the corner / side of the board.

Like many random headlines they may be targeted at people who know something about a topic.

If you know anything about go or computer go from last 10 years then it is obvious which direction the handicap goes.

We are lucky those models need that much compute. If each of them could just spread itself to any cpu like other malware.

Because the computer team in this match for some reason didn't do it. It was like a match vs vanilla stockfish at fixed depth rather than leela chess odds.

Yes, exactly.

The feeling among the go players I know is that the match had been kind of a setup for the human to win.

It's an equivalent of playing in chess with a bishop handicap and a computer playing deterministic chess so that a human can prepare a forced sequence into a winning endgame.

Shin is an absolutely amazing player and not anyone could have achieved that, but nobody really feels like he won vs a computer team that tried its best.