Flavien

546 posts

Flavien

Flavien

@flavienhello

Entrepreneur in AI

Katılım Eylül 2013
774 Takip Edilen192 Takipçiler
Sabitlenmiş Tweet
Flavien
Flavien@flavienhello·
Who am I ? An entrepreneur at heart ❤️‍🔥 Prev accomplishments🎖️: - 2016: created @RpurOfficial with 2k€ student savings -> made 20M€ revenue within 6 years - 2023: create an AI business, got a 1.5M$ buying offer after 4 months, rejected it, raised instead, build it to a 2M ARR business - what’s next 😁📈 ? #startup #ceo #founder #invest #paris #dubai
English
0
0
3
567
Flavien
Flavien@flavienhello·
@Xavier75 insane! when you do start doing phone number other than +33 ? 😁
English
0
0
0
55
Flavien
Flavien@flavienhello·
@steipete what’s the good way of using MCP currently it’s so difficult for me i must be doing something wrong. i launch codex mcp and it never successfully update the agent when its done etc… and its twice as long as sub-agent opus 4.6. any tips ?
English
0
0
0
255
JUMPERZ
JUMPERZ@jumperz·
openclaw dropped a good update and this one is super important for your swarm, but half the features don't work until you manually activate them. >ACP thread-bound agents i was already spinning up subagents in Discord threads to handle tasks. it worked, but i had to manage it myself by checking if they finished, cleaning up dead threads, etc. now openclaw handles all of that. the agent opens a thread, does the job, reports back...i only show up when an actual decision needs to be made. → do this: set spawnAcpSessions: true in your discord channel config >external secrets management my API keys, anthropic, elevenlabs, brave etc, were just sitting in a config file in plain text. anyone with access to that file had the keys. now they live in a separate vault and only get loaded when the system actually needs them. → do this: run openclaw secrets audit — it scans your config and tells you exactly which keys are still exposed and where >agent routing CLI wiring agents to channels used to take a lot of time. now it's just bind/unbind from the cli, so onboarding a new agent takes a minute or even less.. → do this: migrate with openclaw agents bind --channel --peer you have to do all of the above because openclaw ships opt-in features, not auto-changes... anything that touches security, permissions, or routing requires you to do it manually, and these are super important for your swarm. PS: if you're not on Discord, the ACP thread stuff doesn't apply, but the other two do.
JUMPERZ tweet media
English
57
45
965
94.6K
Flavien
Flavien@flavienhello·
@steipete I am ok with config changes frankly as it’s only great stuff. A simple “admin script to update the sub iOS users” would suffice. I could share mine and see if it could be refined I was just looking for group I guess as i am sure it’s a common issue. 😅
English
0
0
0
45
Peter Steinberger 🦞
Peter Steinberger 🦞@steipete·
@flavienhello We have an auto-updater now. The config changes will slow down once we figured out the details, and it will just migrate.
English
1
0
8
3.3K
Flavien
Flavien@flavienhello·
@joshavant @steipete @openclaw nope it won’t as they don’t have the rights as sub user and will break mid task when in need of a doctor —fix that’s why i have a script on the admin session to update them all but i am sure there is thousand of people like me, how do you guys do? 🙈
English
0
0
1
36
Flavien
Flavien@flavienhello·
@steipete So I have build a clunky script trying to update and run everything. but it almost always fail… As i think it’s the most common hardware setup it would make so much sense to have an easy way to update easily. even more with this amazing rate of update 😇
English
0
0
0
43
Flavien
Flavien@flavienhello·
@steipete Any suggestion how to build an auto brew updater on the admin sessions that doesn’t break the build on each of iOS sub users running it? often running the doctor is a mandatory step. which break all
English
2
0
1
4.4K
Flavien
Flavien@flavienhello·
@joshavant @steipete @openclaw yes that’s what i built, now i have a clunky script trying stuff out Haha. As i think it’s the most common hardware setup it would make so much sense to have an easy way to update easily. even more with this amazing rate of update
English
1
0
0
35
Flavien
Flavien@flavienhello·
@joshavant @steipete @openclaw Any suggestion about how to have auto brew updater on the admin sessions that doesn’t break the build on each of iOS sub users running it? it seems than often running the doctor is a mandatory step
English
2
0
0
846
OpenClaw🦞
OpenClaw🦞@openclaw·
🦞 OpenClaw 2026.2.9 just dropped 🔍 Grok web search provider 🧠 No more post-compaction amnesia 🛡️ Context overflow recovery ⏰ Cron reliability overhaul + 40 more fixes from 25+ contributors Elon we added your model btw, you're welcome. github.com/openclaw/openc…
English
449
509
6.1K
705.5K
The Kobeissi Letter
The Kobeissi Letter@KobeissiLetter·
BREAKING: Intel, $INTC, extends its decline to -17% on the day, now on track for its biggest daily drop in nearly 3 years. The US government's position in Intel is down -$4 billion today.
The Kobeissi Letter tweet media
English
157
174
2.4K
319.6K
Nick St. Pierre
Nick St. Pierre@nickfloats·
What comes after ASMR glass fruit cutting and Bigfoot selfie footage?
English
69
5
226
53.4K
Flavien
Flavien@flavienhello·
Just wow! Everything will be accelerated, not just software or “tech” # x.com/DeryaTR_/statu…
Derya Unutmaz, MD@DeryaTR_

Today, I’m sharing another insanely good o1-Pro scientific insight! This one is particularly special to me to a point of making me emotional, its that profound🥹 I asked o1-Pro to critically evaluate a review my students & I had written about a specific subset of immune cells called MAIT cells and their role in cancer. The result? I’m simply shocked beyond belief at o1-Pro’s critiques! 😱They were more insightful than my own—and this is a topic where I’m one of the few top experts in the world, having made some of the key discoveries! As I read through its feedback, I found myself staring at my computer screen, fixated, overwhelmed by a mixture of emotions: disbelief, awe, joy, and a profound sense of humility.☺️Every single point it made, every question it asked—everything was unbelievably insightful! The depth of its analysis is truly hard to comprehend. Even though we believed we had written a great review on the topic, which was accepted with only minor critiques, I was deeply humbled thinking, “I should have addressed and included all these insights in the review.” Ouch! The only solace is that it didn’t find any errors. Seriously, how is this even possible, @OpenAI @sama @gdb?! If o3 is even better, what will this mean? Biology will be accelerated even more than I had imagined. Also I did test o1, Gemini advanced in comparison, they are also excellent models for sure but do not come no where near this level of insight. o1-pro is so special! I’m sharing the feedback in full below. While only a select few with deep immunology expertise may fully grasp the brilliance of o1-Pro’s critiques, I believe it serves as both a historical record of AI’s remarkable advance & a powerful example for other scientists to see how this kind of critical analysis can be leveraged. I will also try to explain these points, although you may want to use Grok or ChatGPT to understand their meaning for now. I also have more stuff to share soon 😊 o1-Pro: Comprehensive Critical Analysis of the Paper This review article provides an extensive overview of mucosal-associated invariant T (MAIT) cells, highlighting their roles in infectious diseases and their paradoxical functions in cancer. While it is broadly informative, a closer examination reveals several areas where the manuscript could be strengthened or where clarity is lacking. Below are key points of critique, organized by thematic areas: 1. Scope and Focus Breadth vs. Depth: The paper covers a wide range of topics—from MAIT cell biology and their role in infectious diseases to their involvement in cancer and even their potential therapeutic application as CAR-engineered cells. While comprehensive, this broad scope sometimes prevents a deep mechanistic understanding in any single aspect. For instance, the section on MAIT cell exhaustion in tumors touches on surface markers and phenotypes but does not delve into the underlying molecular pathways, signaling events, or epigenetic mechanisms that drive this state. Translational Gaps: The authors mention that MAIT cells have therapeutic potential, especially in the form of CAR-MAIT cells or iPSC-derived MAIT cells. However, the review does not thoroughly address the translational hurdles—such as manufacturing scalability, in vivo persistence, and the safety profiles in early-phase clinical trials. The promise of “off-the-shelf” therapies is intriguing, but more practical challenges and limitations should be discussed. 2. Structural and Conceptual Clarity Dual Roles in Cancer: The paper reiterates MAIT cells’ dual nature—both promoting and inhibiting tumor progression. While multiple examples are provided, the narrative could benefit from a more structured framework explaining when and why MAIT cells exhibit opposing functions. For example, are there distinct cytokine milieus, metabolic conditions, or antigenic contexts that tilt MAIT cells from an anti-tumor to a pro-tumor phenotype? A conceptual model or decision-tree figure could have clarified these conditions. Heterogeneity Among Cancers: The review references how MAIT cells play variable roles in different tumor types, but does not systematically compare these differences. Although some tumor-specific data are given (e.g., prostate cancer, colorectal cancer, hepatocellular carcinoma), the text would benefit from a clear comparative analysis: Are there patterns based on tumor origin, mutation burden, microbiota composition, or MR1 expression levels? 3. Mechanistic Details and Evidence Gaps Mechanistic Underpinnings: The review states that MAIT cells respond to microbial metabolites and can become exhausted in the tumor microenvironment (TME). However, it only lightly touches on the signaling pathways, transcription factors, and metabolic cues governing their differentiation, exhaustion, or cytotoxicity. The field’s understanding may be limited, but even a critical mention of the key unknowns—such as how persistent antigenic stimulation via MR1 leads to MAIT exhaustion—would strengthen the discussion. MR1 Expression and Its Regulation: The role of MR1 in tumor recognition is frequently mentioned. Yet, the review does not delve deeply into why MR1 is upregulated in certain tumors, how its expression correlates with tumor progression, or what regulatory pathways control MR1 in cancer cells versus normal cells. These knowledge gaps are worth highlighting since MR1 is central to MAIT cell recognition. Cytokine Signatures and Functional Outcomes: While the review enumerates various cytokines (IL-17, IFN-γ, IL-13) and their potential impacts on the TME, it does not deeply connect these cytokine profiles to specific clinical outcomes or stages of cancer progression. For instance, when do IL-17-secreting MAIT cells predominate, and at what stage of tumor development or therapy might their cytokine shift occur? 4. Conflicting or Insufficiently Addressed Data Contradictory Findings: The review acknowledges that in some cancers, MAIT cell infiltration correlates with poor prognosis, whereas in others it may be linked to a better outcome. However, it does not provide a critical lens on how to reconcile these contradictions. Are sample sizes, patient populations, or detection methods different across studies? Discussing methodological variability or limitations in the literature could guide readers to interpret these discrepancies more cautiously. Microbiome-MAIT-Tumor Interactions: The review emphasizes the importance of the microbiome in shaping MAIT cell function and acknowledges that dysbiosis can alter their activation states. Nonetheless, it does not thoroughly explain which microbial species or metabolites have the strongest correlations with tumor modulation, or how clinicians might manipulate the microbiome to influence MAIT cells beneficially. More detail, even if speculative, would be helpful. 5. Therapeutic Perspectives and Limitations CAR-MAIT Cell Therapy: Although the paper cites promising preliminary work on CAR-MAIT cells, this section would be improved by discussing potential safety concerns, such as off-target effects, long-term persistence, and the risk of creating a new form of immunopathology. The review could also integrate lessons learned from CAR-T therapy (such as cytokine release syndrome and neurotoxicity) and consider whether similar events might occur with CAR-MAIT cells, even if preliminary data suggest otherwise. iPSC-Derived MAIT Cells: While iPSC-derived MAIT cells represent an innovative concept, the review does not critically evaluate the current limitations, such as incomplete recapitulation of the native MAIT repertoire, potential genomic alterations during reprogramming, and the difficulty of producing these at a clinical scale. 6. Methodological Considerations Lack of Systematic Review Methodology: As a narrative review, the paper does not apply a systematic approach to literature selection, potentially introducing bias. Readers would benefit from a brief explanation of how studies were chosen or excluded, as well as a comment on the robustness of the field’s evidence base. Limited Discussion on Human vs. Animal Models: MAIT cell biology can differ between human and mouse models. The review occasionally references murine data without discussing species-specific differences in MAIT TCR repertoire, distribution, or functional responses. This omission might limit the translational relevance for readers focused on human therapeutics. 7. Future Directions and Open Questions More Concrete Future Directions: While the conclusion highlights that more research is needed, it could be more specific. For example, the authors could propose key experiments or highlight urgent clinical trials that would clarify the role of MAIT cells in cancer immunotherapy, or detail which molecular targets (in MR1 or associated signaling pathways) should be prioritized for drug development. In Summary: The review provides a valuable overview of MAIT cell biology and suggests these cells hold significant promise for cancer immunotherapy. However, it lacks deep mechanistic integration, does not fully contextualize contradictory findings, and gives limited attention to the translational challenges of MAIT-cell-based therapies. A more critical evaluation of conflicting data, clearer mechanistic frameworks, comparative analyses across tumor types, and a closer look at the limitations of current knowledge would greatly strengthen the manuscript. Additionally, more structured guidance on future research directions and clinical applications would provide greater value to the field.

English
0
0
0
53
Flavien
Flavien@flavienhello·
Have you ever tried advertising on X tho? it’s the F****ng worst ever! We want to but couldn’t because their algo is basically nothing at all, spending all budget with zero targeting not even spreading it during the day to catch all timezone. Just horrible. @elonmusk please fix that asap. and you’ll become the next Meta. until then. it’s all useless
English
0
0
0
10
Fernando Cao
Fernando Cao@thefernandocz·
In November 2023, Disney tried to destroy X (Twitter). They pulled their ads and cost Elon $75M in revenue. But instead of backing down... Elon told their CEO to go f*** himself. Here's the unbelievable story of how one decision cost Disney $200B:
Fernando Cao tweet media
English
2K
18.9K
151.3K
23.5M
Flavien retweetledi
Thomas Hornall
Thomas Hornall@Thomashornall·
5) Risk Tolerance "Failure" in America's proof you took a big swing and missed … this time. In the UK, it’s like a generational stain we try scrubbing off quietly behind closed doors. No wonder America scales while Britain stagnates
Thomas Hornall tweet media
English
210
849
18.3K
2.8M
Flavien
Flavien@flavienhello·
Poll: Would you consider having an AI companion as part of your daily life? 1. Yes, absolutely! 2. Yes, on top of my normal human interactions. 3. No, I want human interactions only!
Flavien tweet media
English
0
0
0
63
Ejiro Igbesoko
Ejiro Igbesoko@EjiroIgbesoko·
@AdamFard_ Honest question: How do you know what's best for the user? 🤔
English
1
0
2
33
Adam Fard
Adam Fard@AdamFard_·
Mediocre designers do what's easy. Great designers do what's best for the user.
English
3
5
19
1.1K
Shirley
Shirley@theshirleyko·
@Codie_Sanchez The people you surround yourself with have a gravitational pull. Make sure they pull you up instead of down.
English
1
0
1
117
Codie Sanchez
Codie Sanchez@Codie_Sanchez·
This is called The Spillover Effect. The original study had 2 main findings. Kellogg Insight did a study across 58,000 hours in 11 companies. They found "positive spillover" & "negative spillover." 1) Positive Spillover If you sit within 25ft of a HIGH performer, your performance increases by 15%. You are no smarter, you work no harder... and you're 15% better. These highest performers are not impacted by the low performance of their neighbors. My takeaway = the strong lift up the weak. But there was a second finding too, a much more concerning one... 2) Negative Spillover If you sit near a LOW performer... Things get bad fast. How they define “low performer” in the study is important: These are “toxic workers.” A “toxic” person = someone who ends up being fired for their behavior/performance. On average: • A toxic worker costs a co $12,800 • 2% of all workers are toxic • They infect FAST. And actually – the poison of a toxic worker spans way beyond 25ft. Researchers said, “You can see their negative imprint and negative effect across an entire floor.” So remember: Surround yourself with top performers. It's the easiest cheat code to improvement. Toxicity will poison your entire company. Cut it off before it has the opportunity.
English
43
56
371
37.7K
Clifton Sellers
Clifton Sellers@CliftonSellers·
About to be traveling for the next 5 hours What podcast is a must listen?
English
18
0
18
3.7K