coji 溝口浩二 (@techtalkjp) header
coji 溝口浩二 (@techtalkjp) profile picture

プログラマー。数人規模で作られてるめっちゃ便利なものが好き。react-router, conform, duckdb, kysely 推しです。 🦋https://nitter.cf/t.co/kFNhkfsrTD

日本 東京
Joined May 2008
Photo by coji 溝口浩二 (@techtalkjp)Photo by coji 溝口浩二 (@techtalkjp)Photo by coji 溝口浩二 (@techtalkjp)Photo by coji 溝口浩二 (@techtalkjp)Photo by coji 溝口浩二 (@techtalkjp)Photo by coji 溝口浩二 (@techtalkjp)Photo by coji 溝口浩二 (@techtalkjp)Photo by coji 溝口浩二 (@techtalkjp)Photo by coji 溝口浩二 (@techtalkjp)Photo by coji 溝口浩二 (@techtalkjp)
うちの software factory をまわしてる opus くんが、codex の無限レビュー指摘をご注進してくれるようになってくれてて、とても助かっています。
196
natural-japanese、yomiyasu、スキルなし。 「忖度なし、客観的に、厳しく」という指示で AIに比較評価してもらいました。 AIの書いた文書を AIで直して AIが評価する 結果は 「スキルなしが一番読みやすい」 これは、どう解釈するといいのかな。。 どう思います? 詳細 artifactshare.com/a/gr30zia9…
2
9
4
105
10,472
えええほんとすかこれ
As someone who has personally spent $500k / mo+ on Google Ads for years, I can tell you with certainty: This revenue growth in Search is artificial & extremely unhealthy for Google’s business long term Search volumes are declining as legacy search is being increasingly cannibalized by non-monetized LLM queries Google’s response? Manufacture revenue growth via short-sighted, highly extractive, customer-hostile tactics. I.e. charge advertisers more for lower quality clicks, including clicks they do not want and explicitly did not approve Google to charge them for A few examples to illustrate: For all of its history until recently, Google operated on a 2nd price auction model I.e. if you bid $5 CPC and the next highest bidder bids $1 CPC, Google charged you $1.01 for the click (one penny more than the 2nd highest bidder) rather than the $5 you bid This was a genius move by Google early on as it incentivizes advertisers to input their true maximum willingness to pay rather than trying to play the game of bidding low and constantly adjusting to try to stay just ahead of the next highest bidder while still not paying too much However recently, Google silently deprecated the 2nd price auction and began charging advertisers as much as their bid and budget caps allow, regardless of what anyone else is bidding It’s a short-sighted cash grab at the expense of the long term health of the advertiser ecosystem Making thing worse, Google also recently nerfed keyword targeting precision Google previously had precise keyword targeting settings that allowed advertisers pick individual search phrases to bid on, defined down to the character w/ exact match or phrase match targeting This was one of the core features that made search advertising magic, enabling advertisers to run extremely precise campaigns based on exactly what their target customer typed But now, even if you bid on a specific term or phrase using the strictest exact -match targeting settings, Google will show your ad across 1000’s of unrelated keywords, labeling them as as “exact match (close variant)” The definition of “close variant” means whatever they want it to and changes constantly. The result is advertisers get billed for clicks that are totally irrelevant to their business and that their targeting settings explicitly forbid Google from targeting. Google does it anyway and there’s no ability to turn this off So now exact match is broad match, and broad match is just meaningless spam This is all very bad for advertisers, but for Google, it allows them to show your ad and bill you for clicks across 1000x more searches that were previously going unmonetized (mainly because they’re garbage queries no one wants) This is how you grow revenue atop declining search volumes Lastly, and perhaps most egregiously, Google quietly stopped respecting budget caps by a factor of 2x. For example campaigns we’ve been running for years with $1000 daily budget caps suddenly began spending $2000+ per day And the extra spend is entirely on the garbage keywords Google arbitrarily throws in as “exact match (close variants)” which have no value to our business, but can’t be turned off Google offers no refunds nor any recourse for overspend or spend on keywords you explicitly did not target These are not the actions of a healthy business. These are the actions of company whose core business is in decline but desperately needs to pump quarterly earnings so Wall Street will continue to fund insane capex while hopefully looking through their rapidly deteriorating negative free cash flow Google operated a benevolent monopoly for the better part of 25 yrs Meaning the value Google captured from Search was but a small fraction of the value it created, and that spread produced a potential energy that justified expectations of high earnings growth far, far into the future This is now no longer the case At the alter of AI capex, Google is sacrificing the golden goose
4
843
結論: 文字組みをやれ。 学習方法はAIにきけ。 学習は自分でやれ。
3
406
明日これに参加してLTさせていただきます。 デザイン経験ゼロだけど、もう雰囲気でデザインしたくない。 この時代にどうやってデザインの学習をすればいいのか考えたい!
いよいよ明日10/29(木)は「デザインハーネス The Beginning」です📣 ファインディ、TechTalk、ハンディ、Gaji-Labo、noteの5社が、デザインハーネスを始めて運用するまでの試行錯誤を話します! peatix.com/event/5209279 #初めてのデザインハーネス
2
15
1,245
coji 溝口浩二 retweeted
Astra でレビューループ回しまくると実際「論理的には」正しいが実用上ほとんど発生しないような重箱の隅ばっかネチネチ指摘してくる(アスペなので)し、Opus 5.5 が論理的に正しいからと折れて報酬ハックし始めて時間を無駄にするところが起きがちなのなんとかならねえのか?
3
58
42
490
235,400
ついでにスキルに含まれる不自然な「確かめ」を「確認」にかえておきました。Opus 5.5 ってかんじですね。
1
7
690
coji 溝口浩二 retweeted
「CIが通ったら知らせが来ます」「事実の確かめ」のような、動詞の異常な名詞化はどこから来てるんだ。こんなのは本当にSkillで修正できる問題ではないのでは
最近のClaudeはどう指示しても珍妙な日本語しか書かないので、これはもうSkillでどうこうじゃなくてモデルが日本語非対応と考えるしかないのでは
17
5
117
10,075
健康診断の「Web問診票」サイトが、おそらく PHP 影響でサービス停止していて、当日現地で手書きせよと書かれていてつらい。
1
1
792
めっちゃわかる。ほかには「印」とかも
うちの Claude は「確かめ」という語彙を妙に使いがちで気色悪い・・・・「〇〇の確かめは〜」という意味不明な語彙を使うし普通は「確認しています」とか使うだろって
1
2
725
software factory meetup tokyo #0 の当日のご案内を luma からお送りいたしました。ご確認くださいませ。
12
979
お、CLIなら話を聞く
We launched the Gemini API CLI. A CLI for calling the Gemini API. Give it to the agent you already use (Claude Code, Codex, Antigravity, Cursor, OpenClaw, Hermes...). It's NOT a new coding agent you can use it too: 1. Generate images, video, speech, music. 2. Analyze PDFs, images, audio, video, YouTube URLs, 3. Transcribe recordings to md / json / srt, 4. Run Deep Research in the background. Stateless. No memory, no chat mode. Your agent owns the context and the plan, gemini-api does the API call. Build for Agents, it's self-describing. `--help`, `--dry-run`... Start here: aistudio.google.com/learn/in…
348
coji 溝口浩二 retweeted
やっぱりiPhone Duoにはリモートデスクトップアプリがハマるよなあ!くそう!俺もつくってたんだよ!!!合わせて出そうと思ってたのに審査まる一週間止まってんだよ!!!(昨晩諦めて出しなおした) こんなのです。審査通ったら出すのでお待ちください…自分で使ってても超べんりです… casement.win
7
131
8
615
65,510
opus 4.8 + gpt-5.5の組み合わせで作ってたルー大柴UIコピーを opus 5.5 で全部書き直してもらう作業
1
308
Inner Loop と Outer Loop とかよりも、 もっと大きい 創る => 作る => 売る のループをつくりたい。 OODAだとおもうけど、 Fable でもキツいんだよな。 ハーネスほしい。人とAIとその組織に対するハーネス。 現代の大リーグ養成ギプス。
1
372
coji 溝口浩二 retweeted
Made a skill for dimensional drawings of UI components. Inspired by Apple's accessory drawings, it documents a component's architecture into a spec sheet. github.com/enesozturk/dimens…
41
166
19
3,302
139,569