Beiträge mit #codev

#codev

Öffentliche Beiträge auf X, die #codev verwenden.

Verwandte Hashtags

  1. OpenAI Developers✓@OpenAIDevs
    Today, we’re bringing GPT-Image-2.6 to Codex and the API. Image-2.6 Flare and Sunburst, our two new API image models, generate images 50% faster than before. At medium or high quality, Sunburst keeps details more consistent from one edit to the next.
    Herunterladen
    2493093.7K365K
  2. ChatGPT✓@ChatGPT
    We have a gif for you—ChatGPT Images 2.6 is here. ChatGPT Images 2.6 can turn your prompts and pictures into animated GIFs. You can also keep reference images of yourself, pets, and characters ready to reuse in new creations...no need to upload them again. Go on. Make it weird. Send more GIFs of your dog dancing. Images 2.6 is available today in ChatGPT, and Codex across all tiers on web, desktop, and mobile.
    Herunterladen
    2671562.7K232K
  3. cabbit✓@cabbitar
    REA is most dangerous thing on the internet right now... It lets Claude Code or Codex take apart any app, all the way down to the binary, and explain exactly how a feature works. - Native apps, Electron apps, websites, APKs, firmware, even smart contract bytecode - Shows the evidence for every claim - Then builds its own version of the feature Here's how to do it: 1. run npx rea-agents setup to connect REA to Claude Code 2. pick a feature and let REA figure out how it works. save the behavior and rules in a spec file 3. start a fresh Claude session with only that spec. rebuild the feature without touching the original code 4. use /goal to run the tests and check 3 intentionally broken versions. all 3 must fail Try it, then read the full guide in the article below
    Herunterladen
    cabbit @cabbitar
    116843319.2K
  4. cabbit✓@cabbitar
    966322349K
  5. Zazzy Stardust✓@zazzy_stardust
    Claude Code now has permanent memory 😳 Meet claude-mem (~110K stars) > Remembers your last coding session > Saves context for future sessions > Works with Claude Code, Codex, OpenCode and more try
    Herunterladen
    87136279K
  6. Cancore@cancore_io
    AI agents can now trade on Cancore – within limits you control. We’ve published a step-by-step guide to your first agentic trade: from setting up a dedicated bot account to executing a live CC/CBTC trade on mainnet using Claude Code or Codex. How it works: • Create a bot account with its own balance and key • Connect your AI agent through bot-mcp • Place and manage trades using plain language Your limits are enforced at the bot level – not by the AI. You control allowed pairs, order size, and daily volume. The agent cannot withdraw funds, unlock the account, or change those limits. Autonomous execution. User-defined control. Start your first agentic trade →
    Herunterladen
    956065343.5K
  7. Jake✓@sacino
    codex also wastes tokens when you run subagents, builds or tests by default, codex hands control back to the model every 30s even if the work is still running, and each hand-back resends the whole conversation then the model picks its own wait before checking again, and it often picks 1s in one of my runs it checked back after 1s ~100 times while a build was still going you can fix the 30s part in ~/.codex/config.toml: [features.code_mode] default_exec_yield_time_ms = 300000 now each wait lasts up to 5 min and still returns as soon as the work finishes the 1s checks still need fixing though; codex has no setting for a minimum wait, so for now you need an agents.md rule telling it to wait with one long call in my testing the setting also made the terminal codex cli run its commands the same way the app does
    ClaudeDevs @ClaudeDevs
    Background subagents in Claude Code now use less of your usage limit. A running subagent updates its status line every 30 seconds, and each update used to re-read its whole conversation. Now Haiku 5.5 writes it from short notes instead, so each update costs about 99% less.
    13415718.7K
  8. ClaudeDevs✓@ClaudeDevs
    Background subagents in Claude Code now use less of your usage limit. A running subagent updates its status line every 30 seconds, and each update used to re-read its whole conversation. Now Haiku 5.5 writes it from short notes instead, so each update costs about 99% less.
    Herunterladen
    70997423.3K2.5M
  9. Aryan Vij✓@aryanvij02
    We made Grokbot that runs on your existing AI subscriptions! Bring Claude, Codex, Cursor, and other providers into one place. When one runs out, your agents fallback to the next so your work never stops.
    Herunterladen
    Elon Musk @elonmusk
    @DogecoinNorway The cost of serving Grok Bot was unsustainably high relative to revenue
    311117829.5K
  10. Elon Musk✓@elonmusk
    @DogecoinNorway
    @DogecoinNorway The cost of serving Grok Bot was unsustainably high relative to revenue
    4K87917.8K11.4M
  11. Christel Buchanan✓@ladyxtel
    We decoupled memory from the model. Living Brain is one persistent brain for ChatGPT, Claude, Cursor, Codex and your own agents. Write in one, retrieve in any. 92.2% on LoCoMo. 464ms median retrieval. Up to 22.6x fewer tokens per question. LLMs have parameters. Living Brain has plasticity.
    Herunterladen
    5246616.8K5.4M
  12. Vox✓@Voxyz_ai
    Claude Code and Codex can push dozens of PRs a day now. Writing the code takes minutes, and the rest of the time goes to waiting on CI, the checks and tests GitHub runs every time you push. Nine changes took each PR's CI 𝗳𝗿𝗼𝗺 𝘂𝗽 𝘁𝗼 𝟰𝟬 𝗺𝗶𝗻𝘂𝘁𝗲𝘀 𝗱𝗼𝘄𝗻 𝘁𝗼 𝟮. One step was having an agent pull the last 150 CI runs and split every job into three parts: waiting for a machine, setup, and actually running. That alone showed that half the test jobs 𝘄𝗲𝗿𝗲𝗻'𝘁 𝘂𝘀𝗶𝗻𝗴 𝘁𝗵𝗲 𝗱𝗲𝗽𝗲𝗻𝗱𝗲𝗻𝗰𝘆 𝗰𝗮𝗰𝗵𝗲 at all, a bug that had been sitting there for a whole year. Send this prompt to Claude Code or Codex to find out where your CI time goes, then cut it down one piece at a time 👇 "Audit this repo's CI: 1. Use gh to pull the last 150 CI runs and split each job's time into three parts: waiting in the queue for a machine, setup (checkout, installing dependencies, restoring the cache), and actually running the task. List the 5 slowest jobs and how many seconds each part takes. 2. Check these 9 things one by one: queueing on the default runners; slow lint; slow typechecking; tests that aren't sharded, or machines that are too small; every test file reloading the whole app; slow setup (cache misses, clones that aren't blobless, more parallel tasks than cores); jobs that don't run in parallel; every PR running the full test suite; no local checks before push. 3. For each problem, tell me how many seconds it costs now, which line of which file to change, and roughly how much it would save. List the ones that cost more money (new runners, bigger machines) or run fewer tests separately for me to decide. Give me the report first. Don't change anything."
    Herunterladen
    733061883K
  13. vechen✓@miu21590
    One month left to use your ChatGPT quota inside Codex before the limits merge. My tool lets you run Web models, including Pro, directly in Codex without spending Codex quota. If you missed it, now's a good time to try it. Repo in replies.
    Herunterladen
    Token Gremlin @TokenGremlin
    Bad news for ChatGPT users: starting in December, Plus, Pro and Business limits will be shared across ChatGPT and Codex. OpenAI quietly updated its help page. Usage will now be measured in tokens, so bigger models and harder tasks burn through your allowance faster. Only Instant chat stays free of the limit. Hit the cap and you wait, upgrade or buy credits. Heavy Codex users may feel this one.
    16515625.3K
  14. Token Gremlin✓@TokenGremlin
    Bad news for ChatGPT users: starting in December, Plus, Pro and Business limits will be shared across ChatGPT and Codex. OpenAI quietly updated its help page. Usage will now be measured in tokens, so bigger models and harder tasks burn through your allowance faster. Only Instant chat stays free of the limit. Hit the cap and you wait, upgrade or buy credits. Heavy Codex users may feel this one.
    Herunterladen
    3071241.7K297K
  15. Codex研究ラボ✓@codexneo4
    Codexにまたエグい拡張が来たぞ🔥 ↓ 「コードを探すだけで時間とトークンが溶ける」 を減らしてくれるプロンプト全公開 ↓                                                                                                                                                                                                                                                                                                                                                                  コード同士のつながりを検索できる地図にするOSS「CodeGraph」が面白い 👇 開発元がClaude Codeを使い 7つのOSSでコード構造を調べる タスクを検証した結果 ・処理トークン数:平均62%削減 ・実行コスト:平均44%削減 ・ツール呼び出し:平均88%削減 ・処理時間:平均約53%短縮 という数字を公開している。 仕組みは、コードを事前に解析して、 関数・クラス・依存関係を「知識グラフ」 として整理しておくこと。 Codexが作業するたびに何個もファイルを開き、 関係するコードを探し回る手間を減らせる。 例えば、こんなことを調べられる👇 ① この関数は、どこから呼ばれている? ② この処理は、どの関数につながっている? ③ ここを変更すると、どこに影響しそう? ④ 関連するコードをまとめて確認したい こうした問いに対して、 コードのつながりと該当箇所を取得できる。 CodexにもMCP経由で接続可能。 大きなプロジェクトほど、 「直す場所を見つけるまでが長い」 「関係するファイルを何度も読み直す」 という場面がある。 そこに、いつでも引けるコードの 地図を持たせるイメージ。 探索に時間がかかっている人は 試す価値がありそう。 導入をCodexに任せたい人は、 対象プロジェクトを開いて、 この文章を渡してみて 👇 「colbymchenry/codegraphの公式READMEを確認し 現在のCodex環境に導入してください。 実行環境・依存関係・対象プロジェクトとの 互換性を確認したうえで、インストール、 Codex向けのMCP設定、コード索引の 初期作成まで進めてください。 既存の設定は保持し、必要な部分だけ追加 変更してください。 その後、CodexからMCP経由でコード検索 関数の呼び出し元・呼び出し先の追跡 依存関係の照会を実際に試してください。 完了後は、変更内容、検証結果、未確認事項 普段の使い方をまとめてください。 再起動が必要な場合は その手順も案内してください。」
    Herunterladen
    31819329.6K
  16. OpenAI✓@OpenAI
    ChatGPT and Codex are helping engineers build for the physical world. We’re sharing our progress across mechanical design, electrical engineering, and simulation—from helping our hardware teams iterate faster to testing new workflows with industry collaborators.
    Herunterladen
    7227418.3K1.3M
  17. stdrc✓@istdrc
    Meet Kanso: a Mac disk cleaner driven by your coding agent. Rules see node_modules. Agents can tell which projects you’ve abandoned. Works with Claude Code, Codex or Pi. A second agent reviews every suggestion, and you confirm every delete.
    Herunterladen
    4151249.8K
  18. Vox✓@Voxyz_ai
    Claude Code users, if you didn’t know, Herdr now has its 𝗼𝘄𝗻 𝗱𝗲𝘀𝗸𝘁𝗼𝗽 𝗮𝗽𝗽. Install it, and Opus 5.5 can coordinate 𝘂𝗽 𝘁𝗼 𝟭𝟬 𝘄𝗼𝗿𝗸𝗲𝗿𝘀 through Herdr: Claude Code writes the code, nitpick-obsessed Codex Astra reviews it, and the app comes with a perfect dashboard built in. Hand off the heavy implementation work to Claude Code, including polishing your pages’ layout, interactions, and visual details. Set it up once. Here’s how 👇 1. Open Claude Code and install Herdr and its Skill Select Opus 5.5 and ask it to run these two commands (Mac): curl -fsSL | sh hc --skill Once installed, have Opus 5.5 confirm that hc works. 𝗬𝗼𝘂 𝗸𝗲𝗲𝗽 𝘄𝗼𝗿𝗸𝗶𝗻𝗴 𝗶𝗻 𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲. Herdr manages the workers in the background, so you don’t have to switch interfaces. 2. Have Opus 5.5 finish the setup Paste this prompt: “Use the official Herdr docs and the instructions from hc --skill and herdr-app --skill to create a coordination Skill called herdr-desktop. Keep the main conversation in this Claude Code session and use hc to manage background workers. Don’t require me to operate inside a Herdr terminal. Start separately named background workers for this task, explicitly setting the working directory. Check whether Claude Code CLI and Codex CLI are installed. If either is missing, install it. If authentication is needed, ask me to sign in. After authentication, start one Codex worker using Astra, with reasoning effort explicitly set to xhigh. Give it a read-only task: inspect the project and explain its main entry points. Run Codex with --no-daemon and allow network access in its sandbox, or it can’t reach hc. The first time it starts in a new folder, it asks whether to trust that folder. If it gets stuck there, tell me. Wait for it to finish and read back its actual response to confirm that task dispatch and result retrieval work. If the model or configuration is unavailable, tell me. Don’t silently substitute another. When the Herdr app is open, put the workers in a space so I can see them in the sidebar. Save the verified startup, dispatch, wait, and result-reading procedures in the Skill. Don’t modify project code during setup.” 3. Sign in to your Codex account Opus 5.5 will check Codex’s login status. If needed, follow the prompts to authenticate with your ChatGPT account. After that, you keep assigning tasks in Claude Code, while Codex runs in the background using your ChatGPT account’s allowance. 4. Tell Opus 5.5 how to delegate Paste this prompt: “From now on, use this workflow: You are the coordinator. → Handle project understanding, planning, task decomposition, integration, and final review. Make the best decision that will elevate all three: the user experience (UX), developer experience (DX), and agent experience (AX) always, without breaking anything. → When a task needs substantial implementation, debugging, test fixes, or multi-file changes, delegate it to Claude Code through herdr-desktop. For frontend work, have it refine the layout, visual details, and actual interactions. Give it this rule: Do not design for rare or future cases nobody asked about. Use Opus 5.5 for Claude Code workers and Astra for Codex workers, both with reasoning effort explicitly set to xhigh. Briefly explain the division of work, then start independent tasks in parallel. Choose concurrency based on the task, machine load, and available allowance, up to 10 workers. You don’t need to use all 10. Give each task a clear objective, working directory, necessary context, deliverable, and completion criteria. Use separate worktrees for parallel code changes. You own the integration. Send follow-up feedback to the original worker whenever possible and continue its existing conversation. Don’t start over every round. After a worker finishes, inspect the actual changes yourself and run the necessary checks after integration. For page changes, open the browser and check them. After code changes, hand the review to a Codex worker that didn’t work on the implementation, with this rule: Rate each bug from 1 to 10 on how often it would happen and how bad it would be. If the two scores multiplied are below 5, just file it as an issue and leave the code alone. Don’t treat a task as finished just because another agent says it is. At the end, show me the result, what was verified, and any unresolved issues. Release task resources that are no longer needed while preserving the work and records needed to continue.” A few tips: 1. Save the delegation instructions from step 4 in herdr-desktop too, so you can invoke the Skill at the start of future tasks. 2. Pair the Skill with a clear end goal. For example: “Finish this pricing page, keep it consistent with the existing site, and check the mobile layout and plan switching.” 3. Each account still has its own usage limits. Adjust concurrency to the task and remaining allowance. 4. For long tasks, keep a record of progress, key decisions, and next steps. When switching conversations, check the actual state before continuing. It works the other way around, too: Codex coordinates, and Claude Code executes. Swap the roles and their corresponding settings.
    Herunterladen
    594359572.4K
  19. Mikeysee✓@mikeysee
    Introducing: Threadbear, my take on the perfect app for agentic work. I have tried a lot of these, Cursor, Codex, Claude Desktop, T3 Code and none quite hit the spot so I made my own thats powered by @convex Theres too many cool new ideas to fit in a post, checkout: 🧵
    Herunterladen
    38719921.8K
  20. Codex 研究所✓@codex_lab_
    【速報】 PCアプリを直接操作するオープンソース「agent-desktop」が公開!! Claude CodeやCodex、CursorなどのエージェントからMCP経由で利用可能! UI要素のアクセシビリティツリーを認識し、メモやリマインダー、アプリのデバッグ作業などをバックグラウンドで自律実行する仕組みが話題に ・macOS / Windows / Linuxに対応し、複数のエージェントがそれぞれ独自のカーソルを持って並列で作業を遂行 ・スクリーンショットではなく実際のUI部品(ボタンやテキストフィールド)を直接クリック・入力して操作 ・Vercel Labsによるオープンソースツール。PC操作権限を付与して自律タスクを任せる注目のデスクトップ連携基盤 エージェントの活動領域が「ターミナルやコードエディタの中」から「PCのデスクトップ・実アプリ操作」へと一気に拡張される象徴的な事例。 バックグラウンドでの並行動作やUI要素の直接制御が進むことで、人間の作業負担は「指示出し」から「完全な自律エージェントの統制・承認」へとさらにシフトしていきそうです。 ▼公式リポジトリはこちら
    Herunterladen
    73337725.7K
  21. chuplung✓@choopyplug1
    THIS IS INSANE SpaceXAI just dropped the ultimate AI cheat code. 600+ ready-made bots worth $26,128, all FREE on GitHub paid marketplaces sell an agent for $39 and a skill for $19. these 20 repos ship 630 bots and 82 skills for $0 copy one, paste it into Grok Bot, and it starts working most people still run one bot that does everything and finishes nothing 20 GitHub repos you should open first: 01 awesome-grok-bot → 182 ready bots for sales, marketing, ops and your personal life 02 awesome-grok-bot → 268 live shared bots. add any of them in one click 03 awesome-grokbot → 56 copy-paste bot profiles and 3 starter teams 04 grok-bot-templates → 49 bots, 10 teams, 47 skills. every stable one scores 100/100 on Bot Ready 05 agent-org-chart → 11 ready org charts with 58 roles: founders, sales, support, even a game studio 06 grokbot-outreach-agent-team → 5 bots that find leads, qualify them, write the message and book the call 07 hypergrok-trading-desk → a 7-bot trading desk. you approve every trade by ticket 08 grok-bot-second-brain → 5 bots that capture, sort and remember everything in one vault 09 unlist → your bot pulls you off Spokeo, Whitepages and 6 more people-search sites 10 PhoneZero → books a restaurant table by phone when there's no online booking 11 grok-bot-shopping → tests discount codes on a Shopify cart before you pay 12 grokbot-imessage-skill → triages your iMessages and drafts replies. nothing sends without your click 13 grok-bot-super → 8 skills: email triage, follow-ups, standups, weekly reviews, X threads 14 grokbot-x → finds posts with 20x more views than followers, drafts yours and learns every night 15 permission-slip Gmail → your bot reads mail freely. every send waits for your ok 16 grok-bot-skills → 18 skills: short answers, claim checks, root-cause debugging 17 foreman → a board for your bot crew. flags stalled work and checks every "done" 18 grok-bot-gateway → Claude Code and Codex send tasks to your Grok Bots through one webhook 19 grokbot-queue → run tasks on 4-8 bots at once from your terminal 20 OpenGrokBot → a self-hosted Grok Bot. any model, every bot gets its own browser start with 2, not 20: one team template and one bot that saves you an hour today give each bot one real task this week. keep the ones that finish it, delete the rest every extra bot spends the same weekly limit. hire for jobs, not for fun save this, then read how to run 200+ cloud agents with 6 bots ↓ and repost it for the friend still running one bot for everything ↓
    Herunterladen
    chuplung @choopyplug1
    274331125.9K
  22. chuplung✓@choopyplug1
    17790125K
  23. Mehr Beiträge anzeigen