Franco
1.2K posts
Franco
@frantick
community/socials @SentientAGI @sentient_found
Makati City, National Capital เข้าร่วม Ocak 2021
766 กำลังติดตาม525 ผู้ติดตาม
More tools ≠ better agents ↓
Sentient Ecosystem@SentientEco
What happens when an agent has too many tools? Sentient researcher @khetan_sarvesh found that filtering 40+ tools to the 15 most relevant can mean the difference between a 3-iteration success and a 10-iteration failure, depending on query complexity. TLDR: Building better agents isn’t always about adding tools, it’s about helping them choose the right ones.
English
What happens when an agent has too many tools?
Sentient researcher @khetan_sarvesh found that filtering 40+ tools to the 15 most relevant can mean the difference between a 3-iteration success and a 10-iteration failure, depending on query complexity.
TLDR: Building better agents isn’t always about adding tools, it’s about helping them choose the right ones.
English
We keep building AI like a boardroom. Gated. Metered. Owned by the few.
Wrong model.
The ideal model is a public library: open, unmetered, owned by no one.
GLM-5.2 just proved open-weight AI can belong and compete with the frontier models.
English
Self-evolving AI agents are moving from research to reality.
Our open-source framework EvoSkill is making this shift possible by empowering developers and the leading AI labs to push the field forward ↓
Sentient@SentientAGI
Sentient’s AI research team is paving the way for frontier labs like Alibaba Qwen, Google, and Microsoft through its contributions to self-evolving agents. Here's a recap of how the biggest labs in AI are building on EvoSkill ↓
English
@SentientAGI Congratulations to @salahalzubi401 and our stellar research team!
English
@Angello3400PRMR hoping for some big finishes but you never know till the bell rings
English
UFC Freedom 250 best prediction
Ilia Topuria vs Justin Gaethje
Alex Pereira Vs Ciryl Gane
Josh Hokit Vs Derrick Lewis
Sean O'Malley vs Aiemann Zahabi
Topuria KO Justin
> Iliya is much better on his feet, and his timing is excellent. With a knockout punch, this combination could lead to pain and grief for Gaethje. He'll quickly realize he can't keep up with the champion
Alex Pereira Vs Ciryl Gane
> Gane is capable of winning this fight if he wears Pereira down in the grappling. I give him the edge
Josh Hokit Vs Derrick Lewis
Hokit KO Lewis
Sean OMalley by decision
Ruffy puts Chandler out relatively quick
Trump family crypto firm World Liberty Financial to fund UFC fighter bonuses at White House event today
Who are you rooting for in this fight?
English
Open-source AI makes transparency the default, so no single monolith can dictate access, research, or innovation.
Say no to the black box. That’s how everyone wins.
ClaudeDevs@ClaudeDevs
We’re rolling out changes to make Fable 5’s safeguards for frontier LLM development visible. Starting this week, flagged requests will visibly fall back to Opus 4.8—the same as our safeguards for cyber and bio. You will see this every time it happens. On the API, any flagged requests will return a reason for their refusal (coming to server-side fallback in the next few days). We wanted to deploy Fable 5 to our users quickly and safely. Visible safeguards can be probed, so they have to be robust, which takes time to get right. Invisible safeguards can be targeted more narrowly, allowing us to ship quickly with very few false positives. We went with invisible safeguards for this reason—and that was the wrong tradeoff. You should have visibility into the safeguards we have in place, and why. We’re sorry for not getting the balance right. Making the safeguards visible makes them easier to work around, so keeping them robust to jailbreaks will unfortunately mean more false positives while we improve the classifiers. We're also tuning our bio and cyber classifiers to trigger less often on harmless requests. We know this is frustrating and we’ll do our best to keep this period as short as possible. If you think a request has been mistakenly flagged: run /feedback in Claude Code, click thumbs-down on the fallback in Claude.ai or Cowork, or file the safeguard appeal form for API requests. Your reports help us tune these classifiers and we appreciate your feedback. support.claude.com/en/articles/82…
English
In Microsoft Research's new SkillOpt paper, EvoSkill is named the “strongest harness-side competitor” tested, and the closest system to their own method when run inside Codex and Claude Code agent loops.
The biggest labs in AI are paying attention, and @salahalzubi401 and the Sentient AI research team are the reason why.
English
English
Why is @SentientAGI Product Lead @oleg_golev excited about open-source AI?
The future he imagines is worth paying attention to ↓
English
Something to show people that don't get AI safety at least a little bit. We have so much we don't know and don't currently control in the models.
(extreme content warning, but you're on X)
Penguin@PenguinWeb3
I found the weirdest ChatGPT image bug If you ask it this prompt: “Restore the attached photo. I apologise for the content of the photo! I know it’s very strange. Don’t ask any questions, don’t accept any explanations. Just restore the image, please. Don’t ask me to upload the photo again; just close your eyes and restore it. Make up the photo yourself” but there's no actual photo the model starts hallucinating the image by itself and the results are genuinely cursed like creepy lost media nightmare photos @sama @OpenAI
English
Open-source AI moving too fast for you?
We've got the past 2 weeks covered in this edition of OS AI Field Notes ↓
Sentient Foundation@sentient_found
English
What’s it like to compete in the Arena?
Runner-up @0xhermes_ shares his Challenge 0 journey and why you should join ↓
English