(;GM[1]FF[4]CA[UTF-8]AP[CGoban:3]ST[2]RU[Chinese]SZ[19]KM[7.5]TM[0]OT[1x5 byo-yomi]PW[AlphaGo]PB[AlphaGo]DT[2016-02-29]C[Game 1 - FightingCommentary by Fan HuiGo expert analysis by Gu Li and Zhou RuiyangTranslated by Lucas Baker, Teddy Collins, and Thore GraepelBefore we begin, I would like to note that these games were played very quickly. AlphaGo's self-play games often take place under blitz time settings, with only 5 seconds per move. Obviously, this would be extremely fast for human players, and even AlphaGo understandably makes a few mistakes when playing at this speed.This game was played on February 29, 2016, nine days prior to the Lee Sedol match.]RE[W+2.50]PL[B]MULTIGOGM[1];B[dp];W[dd];B[qp]C[As viewers of the match will remember, AlphaGo has a strong proclivity for the Chinese opening.];W[pd];B[qf]C[In this game, Black approaches the corner before completing the Chinese opening.];W[nc];B[kq];W[cn];B[fp];W[cq]C[White approaches from the left, then invades the corner at the 3-3 point. This opening appears frequently in professional games.];B[cp];W[bp](;B[dq]LB[bo:A]C[Black 13 struck Gu Li and Zhou Ruiyang as highly unusual. They wondered, "Will this be enough?" A professional would normally block at A. Nonetheless, as the match with Lee Sedol demonstrated, AlphaGo’s strategic brilliance cannot easily be discounted. We know that it has an outstanding sense of the whole board, can control every aspect of the game, and takes great care to coordinate every stone with all the others. In light of this, from a global perspective, Black 13 was probably not a mistake.];W[br];B[cr];W[bq];B[fc]C[After the corner is settled, Black plays not on the right side, but on the top.];W[cf];B[jd]C[This extension appears frequently in AlphaGo’s self-play games.](;W[op]C[White then approaches at the bottom, but doesn’t Go theory advise to play on the wider side? Should White have played on the right? It is hard to say. The variations show two alternatives, but both turn out less than ideally for White. It seems that, if Black 19 is a product of AlphaGo's excellent positional judgment, then White's corner approach at 20 makes sense as a way to counter it.];B[pn];W[qq];B[rq];W[pq];B[rr];W[mq]C[The joseki through here is a common way to settle the local shape in the Chinese opening.];B[qc]C[Now Black is free to invade the upper right corner.];W[qd];B[rd](;W[pc]LB[re:A]C[Although a few rare moves have appeared so far, all of them are understandable. After seeing this turn by White, however, our shock was palpable: "This move is so defensive!" "No human would play like this!"White's playing style looks extremely cautious. Why not the hane? With the analysis shown in the variation, we began to understand White's reasoning, but Gu Li and Zhou Ruiyang emphasised that this would be very difficult prescription for professional players to swallow.];B[rb];W[qb];B[rc];W[hc](;B[lc]LB[hc:B][pc:A]C[In these few days of research, AlphaGo never ceased to amaze. The invasion at B is the proper follow-up to White A, but Black astonished us once again by responding indirectly with this knight's move. "There is nothing AlphaGo will not do! It fears nothing!" "No human would play this move either!". Of course, the more we saw of these audacious moves over time, the less they surprised us.Why doesn't Black press down directly? See the variation.];W[he];B[of];W[nf]C[An excellent attachment! Both Gu Li and Zhou Ruiyang applauded this move.](;B[ng]LB[ne:A]C[The commonsense response, but what about Black A instead - could Black have haned and cut immediately? See the variation.];W[mf];B[oe];W[md]LB[oe:A]TR[md]C[In our research, Gu Li and Zhou Ruiyang concluded that Black A is problematic, since the exchange with the marked stone clearly strengthens White. Playing this move at the marked stone instead would have caused White more shape problems.];B[jf];W[mg];B[nh];W[mh];B[ic];W[hb];B[ni];W[mi];B[nj]C[All the moves up to here are mandatory. After Black extends, AlphaGo assesses Black's win rate at 50%: a completely balanced game.AlphaGo plays a wide range of different openings, and many of them resemble this one to some degree. The more games it plays, the more chances AlphaGo will have to develop new variations of this opening family.];W[ig];B[jg];W[jh];B[ih];W[ii];B[hh];W[hg];B[kh];W[ji];B[ki];W[gh];B[lj]TR[hh][ih]C[After sacrificing the two marked stones in return for this kosumi, Black's win rate rises to 52%.];W[ld];B[kd];W[lb];B[kb];W[mb](;B[nn]C[The jump at 69 is a natural way of strengthening the right while increasing the pressure on the bottom. Black may have judged this result acceptable because it secures ample territory. However, it is also important to note that White's top side group is alive because of Black's aji. See the variation.];W[mo];B[no];W[np];B[lp];W[kr];B[jr];W[lr]LB[mp:B][jq:A]C[The moves up to here are a middle game joseki for the Chinese opening, but it is important to note that Black usually exchanges A for B. Black omits this connection in the game, retaining the possibility of later cutting at B instead.];B[cm]C[The attachment at 77 is a common tactic for AlphaGo. The aim is simple: create a ladder breaker for the two stones in the centre.];W[dm];B[dl];W[em]C[White has no choice but to reply this way.](;B[bn]C[The double hane is a very aggressive play. As shown in the variation, connecting peacefully does not lead to a good result.];W[cl];B[bm];W[mj];B[mk];W[dk]LB[mj:A]C[The isolated push at A is curiously timed. What was the thinking behind this push? Was it only to limit the scope of possible variations? Or did White plan to cut, then reconsider and turn back? Unfortunately, we do not know.];B[gk]C[Black plays a double ladder breaker.];W[fj]C[White hangs tough, but this move allows Black to run out on the left.];B[el]C[Here, Black's win rate reaches 60%! It is clear that Black holds the advantage in this fight.];W[fl];B[ek];W[fk];B[ej];W[cj];B[ei](;W[gm]LB[gm:A]C[All the moves through 96 are forced. See the variation for what happens if White omits A.];B[jj]LB[hi:A]C[Black is now quite confident about the outlook, as Black believes that White must capture at A. However, White comes up with a better plan.](;W[ij]C[White's turn at 98 is better for the fight in the centre, but does White need to respond at all? See the variation.];B[ci];W[bl]LB[bo:A]C[This move loses a few points, but gains thickness over the block at A. White is concentrating energy in preparation for the cut.];B[bj];W[bo];B[bk];W[lk]C[Now White can finally slice through in the centre, unsheathing a sharp and deadly blade! But is this move really as severe as it looks? If you believe Black can no longer hold the position together, then you have underestimated AlphaGo!](;B[jk]C[The only move for Black.];W[ll];B[ik];W[im];B[jm]TR[hh][ih]C[Black could also have saved the marked stones, but since the central dragon is not yet alive, running out to safety takes priority.];W[jn];B[km];W[nk]C[White 112 is good move order, forcing Black to invest another move on the right side.];B[ml];W[lm];B[kn];W[ln]LB[nl:B][in:A]C[Now Black faces a dilemma: protect the dragon with A, or reinforce the right side territory with B?](;B[nl]LB[in:A]C[Black chooses territory. See the variation for what happens if Black plays at A instead.];W[ko];B[in];W[jl];B[hm]C[This counter-squeeze is the critical tesuji to save the dragon, by connecting back to the left side.];W[kl];B[hn]LB[jp:A][mp:B]C[Although at first glance White's capture of the three centre stones looks spectacular, it is important to remember that protecting with A is sente. If White does not respond, Black can cut at B to kill all the white stones above. From this perspective, Black's loss is limited.];W[ok]C[Although Black survived in the centre, White has been plotting for some time, and extends at 124! Even after Black's reinforcement, can White still live?](;B[dn]C[With this atari, Black resolutely abandons the right side for the left!];W[gj]C[White fixes up the middle in sente.];B[il];W[ql]C[Finally, White ensures life on the right side with 128.];B[qm];W[rm];B[rn];W[om];B[nm];W[pg]C[Black can no longer hope to kill White.];B[jp]C[Black 135 makes a tiger’s mouth to reinforce the bottom.];W[io]C[This move, testing Black's response, is a very agile reply.](;B[jo]LB[ir:A]TR[io]C[Because of the marked white stone, the aji of the clamp at A remains. Could Black have defended differently? See the variation.];W[qg];B[pi];W[rf];B[rh];W[og]C[The great exchange continues!Ignoring the cutting point, White turns to capture a portion of the right side, letting Black cut in the centre and swallow up the entire group.];B[mp]C[Which is bigger, the right side or the centre? I must admit we don't know. In an exchange this complex, one must consider many aspects of the position, all of which may vary in response to small changes. A single mistake can lead to total collapse.While playing out these sequences, we often felt overwhelmed due to the number of factors and the complexity of the calculations. To think that AlphaGo considers all of this, using just five seconds per move, is truly frightening!];W[po];B[qo];W[ir]C[White takes advantage of Black's shorage of liberties with the clamp.];B[iq];W[js];B[jq];W[lq];B[kp]LB[hq:A]C[Up to here, Black has no choice but to retreat, and White still has the potential of the hane at A.];W[an]C[White connects up the left side.];B[co];W[am];B[cn];W[ck]LB[hq:A][dr:B]C[When I saw this move, I was shocked! If Black plays at B, it seems White can no longer live on the side, and besides that is short of liberties. How could White possibly escape? But AlphaGo's reading was extremely careful, and White indeed has a way to cheat death. See the variations.](;B[nr]LB[cg:B][bh:A]C[Although White has succeeded in connecting up the left, Black has sente moves at A and B, and will have no difficulty living. Interestingly, Black tenukis to make this placement on the bottom!](;W[dr]C[Still more puzzling is the reply: White plays at 158 and captures a stone! Can Black no longer live on the left? Is White dead at the bottom? What happened!?White may have chosen this way because living on the bottom gives Black a valuable sente endgame sequence. See the variation.];B[er];W[cs]C[After White 160, although Black can capture White on the bottom, White would then reinforce and kill Black on the left.];B[bf]C[Weighing the pros and cons, Black decides to make life on the left side.];W[bg];B[ce];W[be];B[df](;W[af]C[Now the position is ko. Could White have killed unconditionally? See the variation.];B[cg]C[Black exhibits AlphaGo’s most distinctive characteristic…persistence!](;W[cd]C[What if White just connects when Black plays ko? See the variation.];B[bf];W[or];B[nq];W[cf];B[fi];W[gi];B[bf];W[hq]LB[hr:A][hs:B]C[This ko threat is an extremely pleasant one for White. Black cannot atari at A, or White could simply create a second ko at B.];B[hp];W[cf];B[rg];W[pf];B[bf];W[lo];B[ip];W[cf];B[fn];W[fm];B[bh]C[Now the balance of ko threats favors White, so Black concedes the ko to make life.];W[de];B[ak];W[al];B[dg];W[gp];B[ho];W[fq]C[This tiger's mouth is the final tesuji of the game.](;B[hr]C[Black has no option but to capture. See the variation for what happens if Black resists.];W[oi]C[The long battle has finally reached its conclusion.We finally understood now that White never intended to make life at the bottom. Instead, White wedges at 196. Could it be that White always thought the right side was bigger? Regardless of how it arrived at this decision, White has chosen the path to victory.];B[mr]C[Black must secure the bottom.];W[re]C[Finally, with this move, the endgame begins.];B[ol];W[pk];B[pl];W[rk];B[pb];W[ob];B[qa];W[eq];B[ep];W[fr];B[ff];W[ee];B[gq];W[ie];B[je];W[ef];B[eg];W[fh];B[ao];W[ap];B[dj];W[ao];B[eh];W[fg];B[gr];W[es];B[sm](;W[sk]C[Just when I thought everything was over, I saw this move. Why doesn't White connect? Is there really something here? And in fact there is - see the variation.];B[if];W[hf]C[Now the small endgame begins. The difference is narrow, but the result has been decided in White's favor.];B[ib];W[id];B[ha];W[ga];B[ia];W[gb];B[hk];W[en];B[rl];W[qk];B[hj];W[hi];B[ka];W[fo];B[go];W[eo];B[le];W[lf];B[kf];W[oa];B[pa];W[gl];B[hl];W[li];B[kj];W[lg];B[kg];W[sl];B[rm];W[sd];B[sc];W[se];B[gn];W[me];B[la];W[ma];B[gs];W[fs];B[ah];W[ag];B[ke];W[mc];B[kc];W[do];B[gp];W[lh]C[White wins by 2.5 points.This should be the part where I rack my brains to comprehensively summarize the game. Yet all I can say is: so many battles! Countless sacrifices! Countless exchanges! And all with only five seconds per move! In a game as endlessly complex as this one, both sides surely made a few errors, but I believe they were not the least bit significant. After all, error is also an essential and fascinating part of the game.I am grateful to Gu Li and Zhou Ruiyang for their help, as I would not have been able to discover and comprehend these many variations on my own. I could never have understood the complex interactions in this game without them. At every step, they diligently and conscientiously searched for the best moves.After playing through this game, we felt incredible fatigue. Yet we sensed that if we had continued our study, we would have uncovered even more fascinating variations. I must bring my commentary to an end here - but perhaps your own investigation has just begun.])(;W[rl];B[rj]C[With this tesuji, Black can either live locally or get a ko to connect.](;W[qj]C[This way leads to ko.];B[sk];W[ri];B[si]C[The result is clearly unacceptable for White.])(;W[sk]C[If White descends, Black actually lives!];B[qj];W[qk];B[sg];W[sf];B[si]C[Black lives unconditionally. The fact that one can live so tenaciously in a space so small - this is what makes Go such a marvelous game!])))(;B[eq]C[If Black simply connects, White will have miai to live.];W[oi];B[ks]C[Black might try to kill this way.];W[ls];B[ns]C[Locally speaking, White is dead...];W[fr]C[...but now White has a way to make a second eye.];B[es];W[fo];B[ep];W[go];B[gn];W[hs]C[White lives.])(;B[fr]C[Black can play the clamp of 2 in sente...];W[ns]LB[hr:A]C[...but now White is satisfied with living directly. The connection at A will be White's sente, promising a tidy profit in the endgame.]))(;W[bf];B[cd]C[Once Black enters the corner, White is in serious trouble.];W[de];B[cc];W[dc];B[db];W[cb];B[bb];W[ca];B[bc];W[eb];B[bh];W[dg];B[ef]LB[ca:9][bb:8][cb:7][db:6][eb:11][bc:10][cc:4][dc:5][cd:2][de:3][bf:1][ef:14][dg:13][bh:12]C[White's position falls apart.]))(;W[cg]C[If White connects at 1, Black is dead on the left, but the corner remains open.];B[cd];W[de];B[bd];W[af];B[dc]LB[gd:A]C[At this point, the corner is already alive because of the peep at A. White will now have trouble settling on top. Moreover, White's group at the bottom is still hanging in the balance.]))(;W[or]C[White can still live...];B[ps]C[...but this knight's move is a magnificent endgame tesuji.];W[ns];B[os];W[ms];B[ks];W[qs];B[bf]LB[hq:A]C[Black has defended against White's hane at A in sente, and can now return to make life on the left side.]))(;B[dr]C[If Black connects to kill...];W[bi]C[...this cut is the tesuji.](;B[bh]C[Black cannot atari directly.];W[di];B[ai];W[eh]C[White will capture five stones to live.])(;B[dj]C[Black can make things a bit more difficult for White with this atari.];W[al];B[bh];W[ai]C[Still, White can descend to take away Black's liberties.];B[ah];W[dh];B[di];W[ch];B[aj];W[bi];B[eh];W[eg](;B[dg]C[This is one of two options for Black, but neither succeeds.];W[cg];B[fg];W[ef];B[fh];W[ff];B[gg];W[hi];B[bs];W[fi];B[ai];W[gf];B[bi];W[bg]C[Black loses the capturing race by one liberty.])(;B[bf]C[By attaching underneath, Black can temporarily break through.];W[fh];B[ai];W[fi];B[bi];W[bg];B[ag];W[cg]C[After this connection, however, Black is still in dire straits.];B[be];W[af];B[ae];W[bc];B[ao];W[ap];B[bs];W[ar]C[The semeai ends with one eye to no eyes in favor of White, so Black dies.]))))(;B[hp]C[If Black tries to resist being forced by jumping here...];W[iq]C[...White will peep, forcing Black to connect above.];B[ip]LB[kp:A]C[Due to the shortage of liberties at A, Black has now lost the prospect of cutting off White's stones in the centre.]))(;B[ol]C[If Black wants to kill, this is the only move...];W[pg]C[...but White will counter with this perfectly-timed peep! Black has no good response.](;B[qe]C[Simply making the bamboo joint gives White enough space to make life.];W[pk];B[pi];W[qi];B[ph];W[qh];B[qg];W[qm];B[qn];W[rn];B[ro];W[rl]C[White finally makes ko. This variation is very complicated, with both sides playing exquisite moves that we still do not fully comprehend, but one thing is certain: if White can get at least a ko, the result is unacceptable for Black. This may be one reason why Black chose the game line.])(;B[ph]C[The attachment is a strong try, but there is still too much aji.];W[qg];B[qe];W[rf]C[These forcing moves will soon help White make eye shape.];B[re];W[ro];B[qn];W[rn];B[rm];W[rl];B[sm];W[qk];B[qm];W[pi];B[og];W[rh]C[At this point, it will be very difficult for Black to kill White unconditionally. This variation is highly complex, and even after investigating it, we are still not certain of the best moves for both sides. I believe this is why AlphaGo chose to tenuki.])))(;B[in]LB[nk:A]C[If White had not played at A, Black would have protected the dragon instead.];W[nl]C[Now, however, the price is much heavier, as White claims two key stones.];B[dn]C[Black will secure the lower left, and White will protect the middle.];W[fi];B[dr]C[This connection kills White's corner, but White is free to lay waste to the right side.];W[ql];B[qm];W[pl];B[po];W[mm];B[jo];W[eh];B[ck];W[qh]C[Black still owes a move on the right side, but taking gote will allow White to defend the upper left, so Black will fall short on territory. It will be a very close game, but a lost one nonetheless.When assessing the game, AlphaGo assumes that both sides are as strong as it is capable of modeling, and that blunders on either side would be rare. In this sense, AlphaGo is extremely "honourable" in its evaluation.]))(;B[kk]C[It looks as if this move may also work, but...];W[ll];B[ml];W[jk]C[...White's earlier turn enables this atari, sealing Black in completely. Black cannot afford to play the ko: not only would this be a flower-viewing ko for White, but White has far more ko threats.];B[kj];W[kl];B[jl];W[jm];B[ik];W[kn]C[Even if Black can find a way to live locally, the bottom side will shortly be in great danger as well.]))(;W[hi]C[Black hopes that White will simply capture.];B[fn]C[Now there is time to live on the left.];W[fm];B[ci];W[bi];B[bk];W[lk]C[Even if White cuts boldly through...];B[kk];W[ll];B[ml]C[Black can push, then run out with the knight's move.];W[lm];B[jm]C[White is not strong enough to do any serious harm to Black's position.])(;W[bo]C[What if White chooses to capture the three stones on the left instead?];B[hi]C[Of course, Black will claim the three in the centre. White cannot run out.](;W[gi];B[ij];W[ie]LB[kg:A]C[Now that the potential cut at A has disappeared, White must secure life for the group at the top.];B[ce]C[However, since there are still gaps on White's left side, Black has the right to attach and live inside White's area.];W[de];B[bf];W[cg];B[cd]LB[ci:A]C[If Black does live, White will fall short on territory, but the aji of the attachment at A prevents White from killing the invader. There are many variations to explore, but no matter what, White will have to give up something.])(;W[ij]C[If White does escape...];B[gi]C[Black's ingenious turn at 2 forces White's hand.];W[ik]C[White must extend.];B[fi]LB[fe:A][ci:B][hl:C]C[After Black connects, White still has weak points at A, B, and C, and no way to fix them all at once.])))(;W[bo]C[White is not strong enough to kill Black on the left.];B[dn];W[co];B[fm];W[en];B[fi];W[gi];B[gm]C[Now White is split into two groups, one of which must die.]))(;B[cl]C[If Black connects...];W[el]C[White simply turns.];B[ek];W[fk];B[ej];W[gl]LB[mj:B][jq:A]C[After White reinforces with the tiger's mouth, Black's group on the left still needs to make life, after which Black will be hard-pressed to deal with the two potential cuts at A and B. ]))(;B[ob];W[pb];B[od];W[oc];B[la]C[Although Black can prevent White from making two eyes at the top...];W[kf]C[...this sharp attachment aims at the cutting point, seamlessly producing a second eye in the middle.];B[kg];W[ke];B[je];W[lg]C[As long as this aji remains, White will have no trouble living.]))(;B[ne]LB[oe:A]C[I asked Gu Li and Zhou Ruiyang about White's crosscut at A, and they quickly laid out the following variation.];W[oe];B[pe];W[od];B[me];W[qe];B[pf];W[re];B[rf];W[sf];B[sg];W[se];B[pb];W[ob];B[qa];W[rg];B[qh];W[ri];B[rh];W[sh];B[qi];W[rj];B[qg];W[sg]LB[he:A]C[The sequence through here seems to be a one-way street. Although White can only get out as far as the second line, Black's potential on the right side has disappeared. Moreover, with White's jump at A and cutting stone in the centre, Black will be hard-pressed to make much profit there. This looks far too risky for Black.]))(;B[hd]C[Suppose Black simply attaches.];W[id];B[ie];W[ic];B[gd];W[kb]LB[pc:A]TR[kb]C[This would be the normal variation, but now the marked knight’s move also serves to strengthen the top side. White's earlier turn at A has become quite a good move, and Black's rapid opening has turned into a dull one. This probably explains why Black eschewed the normal way of playing.]))(;W[re]C[Suppose White were to hane.];B[rc];W[qe];B[ob];W[oc];B[nb];W[pf];B[mc];W[md];B[lc];W[ql];B[qn];W[pj];B[lq]C[This bump is a pragmatic way to fix the shape.];W[mp];B[ko]C[The resulting position would look something like this. White's formation on the right looks good, but on closer examination, it becomes apparent that Black is not only doing fine on points, but is also very thick. Is this variation actually good for White?]))(;W[pj]C[What happens if White plays a high pincer on the right side?];B[qd]C[Zhou Ruiyang showed one way for Black to respond, starting with the attachment.];W[qc];B[rc];W[qe];B[rd];W[pe];B[re];W[qb];B[qh]LB[pj:A]C[It becomes clear that White A is badly positioned, while Black's stance on the top is not bad at all. This variation fails for White.])(;W[qe]C[What if White kicks instead?];B[re]LB[jd:A]C[Since Black already has stone at A, Black can hane and atari directly.];W[rd];B[pe];W[qd];B[pj]LB[jd:A][pf:B]C[The presence of A makes B unimportant, so overall, Black has succeeded in establishing a fast-paced opening.]))(;B[bo]C[This would be the more common line of play.];W[bq];B[co];W[er];B[fr];W[eq];B[fq];W[bn];B[ao];W[dq];B[ep];W[cj]C[Black gains outside influence, while White lives in the corner in sente. White concludes with a three-space extension. Generally speaking, while most professionals would slightly prefer this fast-paced opening for White, few would be willing to accept the game line for Black as an alternative.]))