めんふぃむ (@menphim) header
めんふぃむ (@menphim) profile picture

Robot vision engineer. Kaggle Expert(solo: 🥈1🥉4, Team: 😢). Signate Expert(solo: 🥈1🥉2, Team: 😢). Nishika(solo: 🏅1, Team: 😢). AtCoder Algorithm(Cyan).

Joined March 2013
Photo by めんふぃむ (@menphim)Photo by めんふぃむ (@menphim)Photo by めんふぃむ (@menphim)Photo by めんふぃむ (@menphim)Photo by めんふぃむ (@menphim)Photo by めんふぃむ (@menphim)Photo by めんふぃむ (@menphim)Photo by めんふぃむ (@menphim)Photo by めんふぃむ (@menphim)Photo by めんふぃむ (@menphim)
🚨 BREAKING: GEMINI SUBSCRIPTIONS ARE COMING TO HERMES. 🔥 Today, Gemini in Hermes runs on an API key, not the Gemini plan you already pay for. That's being worked on, the approved way: ▸ Nous is working with Google to bring your Gemini subscription into Hermes ▸ It should be officially supported, with Google's sign-off ▸ Apps plugging in a Gemini plan today aren't doing it the way Google approves ▸ Not live yet, no date Claude and ChatGPT subscribers can already bring their plan to Hermes. Gemini is next in line.
283
399
235
4,482
455,438
めんふぃむ retweeted
Microsoft just made Claude Code and Codex cheaper without touching the agent. TokenEconomizer is a free, open-source plugin that learns from the sessions your agent already ran in a repo: - Remembers the repo facts your agent keeps rediscovering - Stops loading tools that never get used, since every tool definition is sent with every request - Works with Claude Code, Codex, Copilot CLI and Pi - 18.4% to 30.9% lower cost across 5 agent-model setups on SWE-Bench If you hit your usage limits every week, this is free money. Save your tokens. github.com/microsoft/TokenEc…
53
184
11
1,655
89,763
めんふぃむ retweeted
KagglerでCSバックグランドがない方はこちらでネットワークの勉強しましょう 経路決定で色々面白いアルゴリズムが使われてたりしますよ youtube.com/watch?v=t0tVQkIA…
4
27
1,779
めんふぃむ retweeted
📊 耶鲁计算机博士生刘晨把自己发 Nature 子刊和 NeurIPS 的论文配图脚本全开源了,figures4papers 让你的论文图一眼看上去就有顶会的样子。 figures4papers 在 GitHub 揽获 1.1 万 star,也上了 HelloGitHub 的推荐。 以前赶论文 deadline,图往往是最后一晚用默认样式凑出来的,配色、字号、图例都不讲究,审稿人扫一眼就觉得粗糙。 这个仓库里放的是作者真实发表过的图:柱状图、雷达图、折线图、3D 球体图、趋势图,每张都配好生成它的 Python 脚本,照着换上自己的数据就能出同款。 更省事的是,figures4papers 里还附了一套科研绘图 skill,能在 Cursor、Claude Code、Codex 里引用,让 AI 编程助手按这套风格直接帮你画。 论文的门面,往往就是那几张图。 GitHub:github.com/ChenLiu-1996/figu…
31
293
12
2,663
205,278
100%同意するけど「自分が考えてる応用に対して評価をどう設計するか」が出来てないのにこういった言説を「最新アルゴリズムの知識を知らなくて良い」叩き棒にしてくる人が現れるのが困るんだよね
AIを10年くらいやってきたんですけど、産業界における良いAIを作るのに最新アルゴリズムの一般知識は今も昔もほとんど効かない(必要になれば調べれば良いので。調べるための素養だけ必要)印象で、とにかく自分が考えてる応用に対して評価をどう設計するかが全てという印象がある。
3
762
・ベーシック認証 ・共有された認証情報 ・13年間パスワードを一度も変えていない ・自社で問題に気づいていない ・発覚後も約1か月放置 ・マスク処理に抜けがある ・共有された認証情報によるベーシック認証だからログを見ても正当なアクセスか不正なアクセスか分からない可能性 ・ほぼ全員が対象 ってこと?
【paiza】約13年間、最大90万2,576件の個人情報に外部からアクセスされ得る状態が継続 2013年の開発用ステージング環境構築時から2026年8月まで、認証情報を長期間変更せず、退職者等がアクセスできる状態になっていたことが判明しました。 対象にはGitHub ID、応募履歴、学習実績、企業担当者情報などが含まれます。 さらに、一部のテストデータではマスク処理が未実施だった期間も確認されています。 実際の外部流出や二次被害は現時点で未確認です。 エンジニアはGitHubを装った偽通知、OAuth認証詐欺、採用担当者になりすました攻撃に注意してください。 rocket-boys.co.jp/security-m… #セキュリティ対策Lab #情報漏えい #セキュリティニュース #paiza
1
89
6
419
102,539
OpenAIがロボティクスチーム解散した話。機械学習×ロボティクス学会CoRLでブース取った後に解散した(言語モデルベースのロボ制御に移管された?)らしい。たしかに6月は積極採用してたっぽい。 teapawt.org/sama/status/2061117302… teapawt.org/fortunemagazine/status…
1
14
1
86
11,770
めんふぃむ retweeted
牛逼!谷歌官方刚发的东西,48小时直接干上GitHub热门第一。 AI写前端默认还停在2019年,因为训练数据全是老屎山。 装个技能包直接拉满:通过 56%→88%。 一行命令搞定:npx modern-web-guidance@latest install 212个现代Web特性直接喂给Claude、Codex、Copilot。 仓库地址:github.com/GoogleChrome/mode… 兄弟们,你们觉得下一个该被官方“喂饭”的屎山领域是啥?
165
691
53
9,032
963,115
めんふぃむ retweeted
Some of my takeaways from CoRL 2026: 1. Deployment is key. The most valuable data comes from real-world deployments. Smarter models need fewer interventions, but get more out of them. 2. World models don't need to be explicitly built into the architecture. With the right data, supervision, and context, models can reason through complex situations. 3. To keep advancing, evals are also a bottleneck. Robotics benchmarks need to improve. We should measure speed, reliability, and robustness, not just task success rates. 4. real2sim2real and code-as-policy are gonna play a key role in overcoming the data bottleneck, enabling deployment in narrow tasks, and collecting data to train future policies. Especially useful for industrial deployments, while home environments offer more opportunities for robot learning. 5. Conferences need to change. We already know most papers and demos from X and arXiv. More events that match people by research interests and create meaningful connections, less focus on traditional paper presentations. Adding tracks to CoRL, for example (?). 6. Tactile sensing continues to be hard. Sensors are heterogeneous, data is noisy and expensive to collect, and there's still no consensus on which sensors to use. 7. A lot of things are still open research. I personally feel we haven't figured out the right recipe for scaling yet. So many questions remain unanswered. 8. More and more people are moving into robotics, and the open-source community is growing. I hope we see more hardware and electronics projects coming out of it. Summer is coming!
11
18
2
152
7,240
めんふぃむ retweeted
You asked for dsh, I added it DeepSeek Harness is the open-source coding agent by @deepseek_ai. It's now on the @huggingface Harness Leaderboard, which compares ten coding agents on the same open models. DSH is statistically tied for first in all five evaluations: DeepSeek-V4.1-Flash and GLM-5.3-Flash at low and high effort, and Flint. It shines on DeepSWE, where agents change code in open-source repositories: 2nd of 10 averaged over the three models, 0.5 points behind Hermes Agent by @NousResearch. On Terminal-Bench's command-line tasks it ranks 6th. One habit explains much of that gap: when DSH finishes a task, it shuts down every background program it started. Three Terminal-Bench tasks ask the agent to start a server, for example a model inference API. The grader tests that server after the agent has finished. With DSH, the server is gone by then. On DeepSeek-V4.1-Flash and GLM-5.3-Flash, DSH passed 2 of 36 attempts on these tasks. @opencode, @pidotdev and Hermes Agent passed all 36. Those three tasks cost DSH 1.5 to 1.7 points in every evaluation. On DeepSeek-V4.1-Flash at high effort, that is more than its 1.3-point gap to the leader. Developer preview: 0.2.2-rc.1. Web search is off because it needs a DeepSeek account key. It costs $0.53 per solved trial, averaged over the three models. Leaderboard: huggingface.co/spaces/joelni…
79
29
14
649
62,190
めんふぃむ retweeted
これはopus-5.5にサブエージェントありでAHC074を解かせたときにどういうサブエージェントを用いたかの履歴で、行き詰まってくるとfresh-eyesというサブエージェントをeffort=maxで起動している
1
34
2,493
Alpamayo 2 Edge x Autowareをリリースしました。VLA基盤モデルによる自動運転AIがすべてオープンソースで手に入ります。 github.com/autowarefoundatio… huggingface.co/nvidia/Alpama…
25
9
156
23,112
めんふぃむ retweeted
We've given all Pro, Max, Ultra, and Team users one free full reset, across all models and limits. Use it anytime before December 10 at 2:00PM PT. We recently fixed a few small issues that used more limits than intended, and the Fable resets didn't do much for those of you who'd already hit your weekly limits for all models. While these issues didn't affect everyone, we want to make up for the trouble. You'll find it in Settings > Usage, or at clau.de/reset.
1,888
2,895
2,005
46,927
3,475,601
claudeもcodexも、未だに自分を人間だと思っているのでこの時間だと出来ないっていうのは確かによく出てくる
213
本質情報だ…!
152
めんふぃむ retweeted
Replying to @wata_orz @thun_c
ベンチマーク用にsandboxを作って内部で実行しているので、メモリ・インターネット・作業ディレクトリ以外へのアクセスも出来ない隔離状態。プロンプト(初回)はこんな感じです。時間を指定するとclaudeが残り時間で出来ることがないと言うので、外部から打ち切っています gist.github.com/wata-orz/75f…
1
1
2
21
2,315
Human in the loop for evaluation -> I'll pass. The main advantage of Kaggle competitions is to have an automated evaluation procedure. The best score submission wins. Simple. As soon as you introduce human ins the loop then you introduce bias. Having some extra prize awarded by a human jury can make sense. But gating submissions with a human evaluation is plain wrong IMHO.
Big news! Today we're launching the competition for Physical-Engineering's Last Exam on @Kaggle, with $400,000 in prizes! 🛠️⚡ LLMs have conquered coding benchmarks—but can your agent engineer the physical world? Today, the best agent scores under 50%. The headroom is massive. 🚀
4
5
1
63
4,283
めんふぃむ retweeted
Replying to @cradrrat
We have dumped JAX/SGLang and rewritten the entire RL and inference stack from scratch in C/C++, which took some extra time. Training (aka pre-training) is done. Lot of cleanup was needed on the SFT data to get that mostly right. Now, 4.8 is in RL and the evals are starting to climb. We will do a soft rollout to Bot users later this week and see how it goes. Grok 4.8 will bear no resemblance to 4.7 (thankfully). It is not yet incredible, but, this time, the foundations are built right, so I expect it to evolve to be something special.
1,689
1,586
1,064
29,286
4,205,197
めんふぃむ retweeted
テキサスでロボット学習の国際会議やるとこうなるんだな
2
31
2,522