Science

Big breakthrough: A few months my lab at MIT introduced SPARKS, our autonomous scientific discovery model. Since then we have demonstrated applicability to broad problem spaces across domains from proteins, bio-inspired materials to inorganic materials. SPARKS learns by doing, thinks by critiquing itself & creates knowledge through recursive interaction; not just with data, but with the physical & logical consequences of its own ideas. It closes the entire scientific loop - hypothesis generation, data retrieval, coding, simulation, critique, refinement, & detailed manuscript drafting - without prompts, manual tuning, or human oversight. SPARKS is fundamentally different from frontier models. While models like o3-pro and o3 deep research can produce summaries, they stop short of full discovery. SPARKS conducts the entire scientific process autonomously, generating & validating falsifiable hypotheses, interpreting results & refining its approach until a reproducible, fully validated evidence-based discovery emerges. This is the first time we've seen AI discover new science. SPARKS is orders of magnitude more capable than frontier models & even when comparing just the writing, SPARKS still outperforms: in our benchmark evaluation, it scored 1.6× higher than o3-pro and over 2.5× higher than o3 deep research - not because it writes more, but because it writes with purpose, grounded in original, validated compositional reasoning from start to finish. We benchmarked SPARKS on several case studies, where it uncovered two previously unknown protein design rules: 1⃣ Length-dependent mechanical crossover β-sheet-rich peptides outperform α-helices—but only once chains exceed ~80 amino acids. Below that, helices dominate. No prior systematic study had exposed this crossover, leaving protein designers without a quantitative rule for sizing sheet-rich materials. This discovery resolves a long-standing ambiguity in molecular design and provides a principle to guide the structural tuning of biomaterials and protein-based nanodevices based on mechanical strength. 2⃣ A stability “frustration zone” At intermediate lengths (~50- 70 residues) with balanced α/β content, peptide stability becomes highly variable. Sparks mapped this volatile region and explained its cause: competing folding nuclei and exposed edge strands that destabilize structure. This insight pinpoints a failure regime in protein design where instability arises not from randomness, but from well-defined physical constraints, giving designers new levers to avoid brittle configurations or engineer around them. This gives engineers and biologists a roadmap for avoiding stability traps in de novo design - especially when exploring hybrid motifs. Stay tuned for more updates & examples, papers and more details.

Most companies take days to make product decisions. We do it in 10 minutes. At Duolingo, Product Review (PR) is the heartbeat of our product development – and probably our most important meeting (of course, I’m biased!). When I joined Duolingo almost ten years ago, product decisions happened casually, often in informal chats at our desks. It worked for a while, but as we grew, it became a mess – key stakeholders were left out, and sometimes it wasn't clear if decisions were final or just thoughts. Over the years, we’ve transformed Product Review into a structured, efficient process that helps us move fast while also maintaining the bar for quality in our product. Here's how our Product Review works: -Each proposal gets exactly 10 minutes (down from 20, initially). The rationale for this length is because we want people to have clear, concise, and strong convictions. This saves time, but it also ensures what they are presenting is something they believe in. Luis von Ahn, our CEO, attends every single meeting. -We have three review formats based on the development stage: one-pager reviews for initial ideas, 1.5-pager reviews for concepts with rough designs, and spec reviews for fully fleshed-out features. -Reviewers are clearly marked and give feedback in a specific order, creating structure. (We also periodically switch up who the key reviewers are.) The meetings are open to anyone in the company. Beyond transparency, this serves as a training ground for developing product sense. -After each two-hour block of reviews, we hold a 15-minute debrief to evaluate decisions and continuously improve the process itself. The result? Fast decisions – but also enough structure to maintain our standard of quality across the app. Here’s a 1.5-pager from Emilia Cabrera, a product manager on our team, about an improvement for our streak session end screen. #productmanagement

We’re planting trees — but losing biodiversity. Global efforts to restore forests are gathering pace, driven by promises of combating climate change, conserving biodiversity, and improving livelihoods. Yet a recent paper published in Nature Reviews Biodiversity warns that the biodiversity gains from these initiatives are often overstated — and sometimes absent altogether. Forest restoration is at the heart of Target 2 of the Kunming-Montreal Global Biodiversity Framework, which aims to place 30% of degraded ecosystems under effective restoration by 2030. But the gap between ambition and outcome is wide. "Biodiversity will remain a vague buzzword rather than an actual outcome" unless projects explicitly prioritize it, the authors caution. Restoration has typically prioritized utilitarian goals such as timber production, carbon sequestration, or erosion control. This bias is reflected in the widespread use of monoculture plantations or low-diversity agroforests. Nearly half of the Bonn Challenge’s forest commitments consist of commercial plantations of exotic species — a trend that risks undermining biodiversity rather than enhancing it. Scientific evidence shows that restoring biodiversity requires more than planting trees. Methods like natural regeneration — allowing forests to recover on their own — can often yield superior biodiversity outcomes, though they face social and economic barriers. By contrast, planting a few fast-growing species may sequester carbon quickly but offers little for threatened plants and animals. Biodiversity recovery is influenced by many factors: the intensity of prior land use, the surrounding landscape, and the species chosen for restoration. Recovery is slow — often measured in decades — and tends to lag for rare and specialist species. Alarmingly, most projects stop monitoring after just a few years, long before ecosystems stabilize. However, the authors say there are reasons for optimism. Biodiversity markets, including emerging biodiversity credit schemes and carbon credits with biodiversity safeguards, could mobilize new financing. Meanwhile, technologies like environmental DNA sampling, bioacoustics, and remote sensing promise to improve monitoring at scale. To turn good intentions into reality, the paper argues, projects must define explicit biodiversity goals, select suitable methods, and commit to long-term monitoring. Social equity must also be central. "Improving biodiversity outcomes of forest restoration… could contribute to mitigating power asymmetries and inequalities," the authors write, citing examples from Madagascar and Brazil. If designed well, forest restoration could help address the twin crises of biodiversity loss and climate change. But without a deliberate shift, billions of dollars risk being spent on projects that plant trees — and little else. 🔬 Brancalion et al (2025): https://lnkd.in/gG6X36WP

If your paper is getting rejected, it isn’t necessarily the science that’s the problem (it’s likely the journal fit that’s off!). Here’s how you can be be strategic about journal selection. How do I choose the right scientific journal? ↳ Analyze your citation list and target relevant publications. Can impact factor really determine journal quality? ↳ Look beyond numbers, focus on specialized audience fit. How to avoid predatory journal publication traps? ↳ Verify journal reputation before submitting your research. Will editors help improve my manuscript? ↳ Follow author guidelines meticulously. Navigating the academic publication landscape can feel like traversing a complex maze. As a professor, I've learned that selecting the right journal is both an art and a science. Here's a game-changing approach I've developed: 1. Conduct a citation audit: Count journals you've referenced most frequently. These are likely your ideal publication targets. 2. Beyond Impact Factor: Don't get fixated on numbers. A lower-ranked journal with a specialized audience might be more valuable than a high-impact generic publication. 3. Beware of predatory journals: If an unsolicited email promises quick publication for a fee, run! Legitimate open-access journals conduct rigorous peer review. 4. Craft a strategic cover letter: Suggest credible reviewers, highlight your paper's novelty, and demonstrate professionalism. 5. Patience is key: Most journals reject approximately 50% of submissions. Don't be discouraged - each submission is a learning opportunity. Pro tip: Always read and follow the journal's specific author guidelines. This shows you're a detail-oriented, professional researcher. Have you ever struggled with selecting the right scientific journal for your research? What challenges have you encountered? #science #scientist #ScientificCommunication #publishing #phd #professor #research #postgraduate

The impact of climate change on the SDGs 🌎 The latest State of the Global Climate 2024 report from WMO provides a clear assessment of how accelerating climate change is affecting global stability. With 2024 recorded as the hottest year on record—1.55°C above pre-industrial levels—the implications extend far beyond temperature increases. The findings highlight the direct and systemic risks climate change poses to achieving the UN Sustainable Development Goals (SDGs). Rising temperatures, ocean acidification, sea-level rise, and glacial melt are driving widespread environmental and socio-economic disruptions. These changes are not occurring in isolation; they are interconnected, amplifying existing challenges related to food security (SDG 2), water availability (SDG 6), economic resilience (SDG 8), and biodiversity loss (SDGs 14 & 15). Ocean changes are among the most critical risks. Increasing ocean temperatures and acidification are disrupting marine ecosystems, reducing fish stocks, and weakening the ocean’s ability to act as a carbon sink. This has significant consequences for coastal communities, food security, and global supply chains. Glacial loss and sea-level rise are reshaping landscapes, affecting infrastructure, water resources, and human settlements. Coastal erosion, land degradation, and increased flooding threaten urban development (SDG 11), economic productivity (SDG 9), and disaster resilience (SDG 13). These impacts also contribute to population displacement, further straining social and economic systems. The increase in extreme weather events, from heatwaves to hurricanes, is exacerbating global inequality. Agricultural losses, infrastructure damage, and rising adaptation costs are disproportionately affecting developing regions, slowing progress toward economic stability, sustainable production, and resource security (SDGs 8 & 12). The WMO report emphasizes that while exceeding 1.5°C in a single year does not mean the Paris Agreement target has been breached, the trend underscores the urgency of reducing emissions and strengthening adaptation strategies. Without immediate action, climate risks will continue to escalate, undermining progress toward the SDGs and increasing long-term economic and environmental costs. Addressing these challenges requires systemic policy shifts, investment in climate resilience, and cross-sector collaboration. As climate change intensifies, integrating sustainability into decision-making at all levels will be essential to mitigating risks and safeguarding global development objectives. Source: State of the Global Climate 2024 #sustainability #sustainable #business #esg #climatechange #sdgs

What happens when companies break their climate promises? Almost nothing. A new study has uncovered troubling truths about corporate climate commitments. Out of 1,041 companies with emissions reduction targets set for 2020: -9% (88 firms) openly failed to meet their goals. -31% (320 firms) stopped reporting on their targets without explanation. What happens when companies miss these targets? Practically no consequences: -Only three failed companies faced media scrutiny. -No significant market backlash, media sentiment shifts, or ESG rating downgrades. In contrast, companies were rewarded with positive press and improved ESG ratings simply for announcing these targets. The bigger issue: This accountability gap threatens the credibility of ambitious 2030 and 2050 climate pledges. Unlike financial targets, which are rigorously monitored, emissions goals often exist in a vacuum—without oversight or real consequences for failure. Interestingly, the study found that: -Firms in common-law countries and those with stronger media accountability had better success rates. -High-emitting sectors like energy and materials struggled the most, with the highest rates of "disappeared" targets. With more companies backing away from climate action, we cannot afford to let this cycle continue. It’s time for corporate sustainability leadership to move beyond announcements and deliver measurable, transparent results. Accountability mechanisms—demanded by both regulators and stakeholders are urgently needed. A great piece of work by Xiaoyan Jiang, Shawn Kim, and Shirley Simiao Lu! Let’s learn from these insights to ensure that corporate climate pledges actually deliver. #climatechange #netzero #esg

The stark contrast in per-capita consumption-based carbon emissions between countries in the Global North and the Global South. This disparity underscores a fundamental inequity: nations that contribute the least to global #greenhousegasemissions often bear the brunt of #climatechange's adverse effects. The graph shows the consumption-based emissions, carbon emissions to the country where goods and services are consumed rather than where they are produced. This methodology reveals the true carbon footprint of a nation's lifestyle. Wealthier nations have higher consumption patterns, leading to more significant emissions. This is not just due to industrial activities but also because of the demand for goods and services that have high carbon footprints. Many developed countries have shifted manufacturing and production to developing nations. While this move reduces their production-based emissions, their consumption-based emissions remain high because they still consume these goods. Developed countries have historically contributed the most to cumulative global emissions due to early industrialization. This historical context adds another layer to the injustice, as past emissions continue to affect the current climate. As we lead to the next round of negotiations at #COP29 we must recognise that those who contribute most to emissions have a greater responsibility to lead in mitigation efforts and provide financial and technological aid to countries in the Global South to help them adapt to climate impacts and develop sustainably.

A couple of news items have me thinking. And frankly, getting a bit agitated. The first was the news that the Kiwisaver gender gap has got worse in the past year. New research from Te Ara Ahunga Ora The Retirement Commission shows a 36 percent gap between the amount men and women are putting into KiwiSaver each year, far outpacing the actual gender pay gap. Men and women are contributing the same percentage of their salaries, but women are disadvantaged by working part-time and taking greater (unpaid) care responsibilities. The other bit of not-unrelated news, is the NZ Herald’s list of top-earning CEOs. Of the top 10 - just one woman. In the 54 CEOs surveyed: seven women. In the immortal words of Carrie Bradshaw: I couldn’t help but wonder… WTF is going on here? How have we not come further? Of those top 10 CEO’s companies, how many are reporting on their gender pay gaps? (The answer, according to the Mind the Gap registry: 4) Is there a relationship between perimenopause/menopause support (or lack of it) and the lack of women in CEO roles in our top organisations? AND between perimenopause/menopause and the Kiwisaver gender gap? I think there might be. We know, for example, from the work of Sarah Hogan who found in her NZIER research that 14% of women said they had to reduce their working hours to manage their menopause symptoms, and 6% had changed roles. Twenty percent of women who experienced symptoms said it would have been helpful to be able to make adjustments, but they never requested any, mostly because of menopause and gendered ageism stigma. All of us who are working in menopause education have heard stories from women who - at a critical stage in their careers in midlife - have made the call to step back rather than step up into senior roles, because of the challenges of menopause and the lack of support for them in their organisations. We have to talk more about this. In fifty years we’ve made so little progress… we REALLY don’t want our granddaughters to be still facing these kinds of shocking statistics in fifty years’ time. 

Text understanding with #LLMs is useful but not enough for scientific understanding and discovery. In chemistry, in addition to text, chemical structure is essential to determine the properties of molecules. We have created the first multimodal text-chemical structure model: MoleculeSTM. It has an aligned latent space of both modalities. This allows the users to provide free-form text instructions to create molecules with arbitrary sets of properties. This enables zero-shot text-guided molecule editing (lead optimization) without the need to fine-tune the model for each new specification. Paper: bit.ly/4736BPH Code: bit.ly/4877YOS The core idea of MoleculeSTM is to align the chemical structure and textual description modalities using contrastive pretraining. The pivotal advantage of such alignment is its capacity to introduce a new paradigm of LLM for drug discovery: by fully utilizing the open vocabulary and compositionality attributes of natural language. To adapt it to a more concrete task, we focus on zero-shot text-guided molecule editing (aka lead optimization). Existing ML-based molecule editing methods suffer from data insufficiency issues. MoleculeSTM circumvents this by formulating molecule editing as a natural language understanding and interpolation problem, which is much easier to solve under the zero-shot setting. Such a novel paradigm is meaningful for addressing more practical drug discovery challenges. We will have more follow-up works along this LLM for the molecule/drug discovery research line. Please stay tuned! Shengchao Liu Chaowei Xiao Weili Nie Zhuoran Qiao Caltech

In Okinawa, Japan, the average life expectancy is 84 years. In India, it's 67 years. That’s 17 years of missed birthdays, moments, and memories. Why? The secret isn’t medicine or money. It’s small, daily habits that protect the body and mind over time. ▶︎ 1. They eat until 80% full It’s called ‘Hara Hachi Bu’. No overeating. No “clean your plate” pressure. It gives their metabolism less to process - and reduces inflammation over time. ▶︎ 2. Daily movement is built into life They follow the principle of ‘Karada O Ugokasu’ - “move your body naturally.” Instead of formal exercise, they walk to visit neighbors, and tend gardens every day. The goal isn’t intensity. It’s consistency through natural motion. ▶︎ 3. Plant-heavy, simple meals Okinawans follow the ‘Washoku tradition’ - a traditional Japanese eating style focused on balance, seasonality, and variety. Their plates are small. Their portions are modest. Even chopsticks help - slowing down eating and reducing bite sizes. ▶︎ 4. Strong community ties They have ‘Moai’ - tight-knit social groups that support each other for life. This community helps lower stress, strengthens immunity, and is linked to reduced risk of chronic disease and early death. ▶︎ 5. Purpose beyond work They call it Ikigai - a reason to get up each morning. Whether it’s mentoring younger generations, work, art, or caring for plants - they stay mentally and emotionally engaged well into their 90s. The result? Lower rates of diabetes, heart disease, cancer, and depression - even in their 90s. Remember, none of this requires more money or more effort. Just small shifts in how we live each day. Hit repost 🔁 if this made you rethink your habits. Someone in your connections might need that nudge too. #health #wellness #longevity