@SentientEcoi
iAccount based inPhilippines!
About this account
- Account based in
- Philippines
- Connected via
- Web
! X says this location may be affected by a proxy or VPN.
Account-level information from X, not a live location or the device used for a specific post.
Empowering @SentientAGI builders, researchers, and the ecosystem in advancing open-source AGI 🤝
Joined July 2024
- Tweets978
- Following75
- Followers27.9K
- Likes1.6K
Same model, different harness, but up to 40x the cost per solved task.
Check out @qzxcle's breakdown of the @SentientAGI x @Princeton paper ↓
New Princeton + Sentient Labs paper shows a coding agent can cost 40x more per solved task by changing only the harness around it, leaving the model untouched.
and controlled swaps show those scaffold differences barely move accuracy.
that the same model passes about the same tasks on any harness, so a leaderboard score does not have to mean the cost you will pay.
The problem is that leaderboards rank by model name while leaving the scaffold undisclosed. The agent may keep taking turns, but those turns can stop editing files or running commands and just burn context.
The paper fixes this by holding model, prompt, sandbox and task set constant while varying only the harness, then reporting tokens per solved task, idle turns and failure mix next to pass rate.
This lets a developer pick the harness and model pair that fits token and latency budget.
I'm 28.
Open-source AI lover, based in Seoul
Looking forward to connect with more global open source builders during KBW! See ya😉
Always w/ @SentientAGI @sentient_found
Last week, Sentient Korea BD @namyura_ joined the Agent Economy panel at Draper Startup House to talk about the new economy AI agents are creating.
Thanks to the @stripe Seoul community for having us 🇰🇷
Save the date: Sentient Korea BD @namyura_ is joining the Agent Economy panel hosted by the @stripe community 🇰🇷
📍 Draper Startup House Korea
🗓️ Sep 14, 2026, 6:30–8:30 PM KST
RSVP: stripecommunity.com/public/c…
More tool variety doesn’t tell you much about whether an agent will succeed.
Across 13K+ OfficeQA runs, successful agents used slightly more varied tools than failing ones, but tool variety alone predicted success only slightly better than a coin flip.
TLDR: Low tool variety may be a weak warning sign. It isn’t a diagnosis and our results show that switching tools is not a fix.
Check out the full analysis by Sentient researchers @iamnamanvats and Deep Halder ↓
nitter.cf/SentientAGI/status/208…
Sentient Ecosystem retweeted
9 月 19 日,Open AGI Builders Day 再次来到上海!
这次我们邀请了来自 AI 产品、Agent、开发者工具与基础设施等不同方向的 Builders,一起分享正在构建的产品,也围绕 Agent 时代的产品、交互与控制,以及 如何从 Demo 走向真正的 AI 生意 展开了两场 Panel 讨论。
从技术到产品,从 Demo 到商业化,感谢每一位来到现场分享和交流的朋友!
Banger paper from Princeton, UW and Sentient.
They show that LLM fingerprinting does not survive a malicious model host.
Listed attacks need no extra model. A host with the weights just perturbs its own decoding, and ten recently proposed fingerprinting schemes stop verifying.
They bypass verification completely on eight of the ten, 94 percent attack success on EditMF and 65 percent on the watermark based scheme. Utility on IFEval, GSM8K, GPQA Diamond and TriviaQA drops under 5 percent in most cases.
The break comes from where the fingerprint lives.
Memorization based schemes overfit on the query and response pair, so the fingerprint token sits at the very top of the output distribution. Suppress that head for the first few tokens and verification fails. Overconfidence on those same tokens tells the host exactly when to suppress, so benign answers stay intact.
Verifier strictness decides the run.
SuppressTop k hits 100 percent against token level prefix matching and only 38 percent against keyword matching. The stronger SuppressLookahead attack closes that gap, dropping Instructional FP from 100 percent verified to 12.5 percent. Intrinsic fingerprints fall even faster. Their GCG optimized queries are unnatural, so a GPT-2 sized perplexity filter separates them from real WildChat traffic and refuses them, 100 percent evasion with no utility cost.
Paper: arxiv.org/abs/2509.26598
그록봇 스타일 케릭터 만들어 주는 프롬프트 공유
grokbot-icon-studio.serio-ai…
파딱이 아니라 긴 텍스트 업로드가 안되어 아예 웹앱 형태로 배포합니다. 다음 사이트에서 복사 버튼을 누르고 사용하는 이미지 생성 Ai에 붙여넣기해서 활용해 주세요
Errors aren't a red flag for agents.
Across 13K+ OfficeQA runs, both passing and failing agents hit errors at nearly identical rates.
TLDR: An error isn't a sign the run is doomed, so counting errors is a bad way to predict failure.
Check out the full analysis by Sentient researchers @iamnamanvats and Deep Halder ↓
nitter.cf/SentientAGI/status/208…
Save the date: Sentient Korea BD @namyura_ is joining the Agent Economy panel hosted by the @stripe community 🇰🇷
📍 Draper Startup House Korea
🗓️ Sep 14, 2026, 6:30–8:30 PM KST
RSVP: stripecommunity.com/public/c…
Sentient Ecosystem retweeted
Replying to @SentientAGI
@jwalin_shah is the kind of engineer I adore - creative problem solving level 10, combined with the humility and open mind that always invites new ideas. You are forever on my short list of dream collaborators for the next thing I build. Your competition is the best ally.
No data controls. No gatekeepers.
That’s the open-source advantage.
There is a super shady data control setting on everyone's ChatGPT which makes it seem like your data can be used for training even if you explicitly say to *NOT* improve the model for everyone (1/9)
Readers added context they thought people might want to know
This claim is false. OpenAI has clarified that the in-app toggle and the privacy portal are independent ways to opt out of data training. You only need to use one method, and OpenAI respects the opt-out choice regardless of where it is set.
x.com/thsottiaux/sta…
help.openai.com/articles/77308…
The people building open-source AI don't get enough airtime.
So we're giving it to them ↓
Highlighting the people moving the open source AI movement forward has been a breath of fresh air.
If your YouTube algo needs a break from all the AI doomposting, I’ve been slowly building up our @openagisummit Youtube
Subscribe here: youtube.com/@openagixyz
Building open-source AI in Shanghai? Come meet the @sentient_zh team on September 19th!
@Anitahityou and @KumaSentIt will be on the ground at OpenAGI Builder's Day, alongside founders, builders, and researchers to discuss what comes next for AI.