Brian Barela

@CornellBaseball Despite recording 19 hits, including a five-hit performance by sophomore catcher Mason Barela, @CornellBaseball drops the series finale to Fordham, 16-11, as its ninth-inning, two-out rally fell short, leaving the tying run at the on-deck circle. #YellCornell

Let’s goooo!

@its_tianyi @headinthebox 100% even a small dip in accuracy or change in output is a massive impact on a prod app

@headinthebox The real timesink is maintaining all the prompt engineering tricks that stop working 3 months later when the next model just handles it natively.

The bitter lesson of building LLM apps: models are getting smarter faster than you can hack around their current limitations.

@vhmth @bryan_johnson Wise words here

Bryan I’ve done 5-7g of shrooms 4x in my life. I’ve also done 5-MeO-DMT and have experimented with large quantities of acid many times. People call people like me “experienced”. Or “washed out” I guess lol. When you do 5g at once, you are going to go on a spiritual journey. Know many people are telling you this already, but the entire clinical rational frame you typically hold will completely dissolve. I highly doubt you are going to want to do this multiple times let alone once a month of several in a row. Prepare and be ok with that. I don’t think doing 5g your first time is too much because there is nothing that’s going to prepare you for this. I would recommend NOT live streaming this. I would recommend NOT having a bunch of people watching you and taking measurements. I would prepare for the journey to take you. You can say you want music and this and that and it will all go by the wayside. God speed.

What is your recommended playlist for a 5 gram magic mushroom journey…

@mramiracle @gabriel1 10000% agree

@gabriel1 You’ll suffer no matter what, you might as well find something worth suffering for. Plus it’s inevitably the only road to self actualization, to work with something you’re innately good at, and is authentic to you. The inverse will lead you astray; an unhappy, and depressed.

the average person spends 0.0001% of their life time trying to earn more, have better colleagues, and making sure they love what they do, and then spend 60% of their lives doing that work

One UX challenge in GenAI systems isn’t the model itself — it’s how users experience the data behind it. With data from multiple sources or on different schedules, late-arriving fields or partial records are inevitable. --> The key is to design for transparency

@julianhyde cool! taking a look!

@brianbarela That would be awesome. Would you like to pick up an issue? Or suggest a task that you'd enjoy doing. (Start small!) github.com/hydromatic/mor…

If you would like to help implement a new functional / query language, we'd love your help, and now is a great time to join the project. #rustlang

Jeff Bezos explains the idea of “paper cut” teams “There are big things that are really important to manage — and by the way, it’s astonishingly hard to focus on just the big things. Even though they’re obvious, they’re really hard to focus on. But in addition to that, there are all these tiny customer deficiencies. We call those ‘paper cuts,’ and we make long lists of them. Then we have dedicated teams that go fix paper cuts. That’s because the teams that are working on the big issues never get to the paper cuts. They never work their way down the list. They’re working on big things — as they should and as you want them to — so you need special teams who are charged with fixing paper cuts.” Video source: @lexfridman (2023)

@pateljm @Informatica @CMUDB @JiaZhihao Would love to connect re Datachat!

na.magazine.intelligentcio.com/p14 Excited to announce a unique partnership between @Informatica and @CMUDB to tackle current and future challenges in data exploration, understanding, cleaning, and analytics. Thanks @JiaZhihao for playing a pivotal role in this partnership. Looking forward to working with Rik Tamm-Daniels, Suresh Bathini, @gauravpathak and their team!

Resume / LinkedIn / Interview Help open.substack.com/pub/brianbarel…

Jumping ahead early! Freshman catcher Mason Barela capitalizes on a leadoff walk drawn by sophomore shortstop Kevin Hager, registering his second home run of the season to put @CornellBaseball ahead 2-0 in the second inning. 📺: bit.ly/3EEoIU6 #YellCornell

So proud!!!

@andrewchen Also lots of assumptions that companies will let AI generated outputs “pass” without human validation Does not take into account industries w strict data governance and regulations

ChatGPT's perspective: If AI aggressively replaces business process outsourcing (BPO) and outsourced IT services in India, the economic implications would be profound, multifaceted, and transformative. India’s economy relies heavily on IT-BPO sectors, making this disruption critical. I’ll explore the implications comprehensively across multiple dimensions: 1. Economic Impact: Direct Job Losses and GDP Hit • Employment Impact: • India’s IT-BPO industry employs approximately 5.4 million people directly and an additional 20 million indirectly as of 2024. • Aggressive automation could eliminate between 40-70% of these roles due to efficiencies from generative AI models capable of handling customer service, coding, testing, and routine administrative tasks. • Worst-case estimates indicate around 2–3.8 million direct job losses and up to 10 million indirect job losses. • GDP Contribution: • IT-BPO contributes around 8-10% of India’s GDP (approximately $245 billion annually in 2024). • A 50% automation-driven contraction would mean ~$120 billion loss annually, significantly impacting overall growth. • Trade Balance: • IT-BPO contributes to over 50% of India’s service exports, earning foreign exchange crucial for trade deficits. • Massive automation would result in significant reduction of forex reserves (~20-30%), exacerbating trade deficits. Detailed Examples: • Companies such as Infosys, TCS, and Wipro, which have tens of thousands of roles focused on routine coding, testing, and call centers, would face immense disruption. • Small- to medium-sized enterprises (SMEs), comprising over 50% of outsourcing vendors, might face existential threats. 2. Socioeconomic Impact • Middle-Class Disruption: • India’s expanding middle class (~350 million) is heavily supported by IT-BPO jobs. • A sharp decline in these jobs could cause a significant regression, creating downward socioeconomic mobility, reducing discretionary spending power, and shrinking consumer markets. • Urban Migration Reversal: • Cities like Bengaluru, Hyderabad, Pune, and Chennai, heavily dependent on the tech industry, may experience population decline as workers relocate back to smaller towns, reversing decades of urbanization. • Housing Market Collapse: • Real estate in tech hubs (e.g., Whitefield in Bengaluru, Cyberabad in Hyderabad) could face a severe downturn, dropping prices by 30-50%. 3. Impact on Education and Skill Development • Curriculum Obsolescence: • Existing education programs emphasizing basic IT and coding skills would rapidly become obsolete. • Engineering colleges graduating 1.5 million engineers annually would face unprecedented unemployment or underemployment rates, exceeding 60%. • Skill Gap and Re-skilling Crisis: • Massive re-skilling required in AI, data science, cybersecurity, and creative jobs. • India’s current training infrastructure, although extensive, isn’t robust enough for sudden and massive skill migration. Proactive Suggestion: India might require comprehensive national re-skilling initiatives, similar to Japan’s post-automation workforce programs, potentially involving public-private partnerships. 4. Macro-Economic and Governmental Impact • Tax Revenue Loss: • IT-BPO contributes significantly to tax revenues (over ₹2 lakh crore annually). Rapid job loss would severely reduce government income, shrinking fiscal space for investment and social welfare. • Increased Social Spending: • Unemployment benefits, retraining, and welfare programs would dramatically increase, creating budget deficits. • Potential Social Unrest: • High unemployment among educated youth could lead to political instability and social tensions, affecting governance and foreign investment. Speculative Scenario (High Likelihood): • Central government intervention via massive fiscal stimulus or guaranteed basic income programs might become necessary to maintain social stability. 5. Positive and Contrarian Impacts • Increased Productivity and Efficiency: • AI could enhance productivity significantly in non-automatable roles, pushing India up the value chain, from low-end coding and services to specialized high-end AI management, data science, and strategic consulting. • Innovation Boost: • Potential for significant innovation as Indian tech leaders redirect human capital toward AI research, quantum computing, cybersecurity, biotech, and advanced manufacturing. • Indian startups in AI-driven fields may flourish dramatically (e.g., Zoho, Freshworks, Postman may transition successfully into AI-native companies). • Cost Optimization and Competitiveness: • Lower operational costs from automation could attract advanced manufacturing (semiconductors, electronics, AI hardware) or research-intensive industries from China or Europe, offsetting outsourcing losses. Proactive Suggestion: India could aggressively adopt proactive regulatory frameworks (similar to the UAE or Singapore) to encourage rapid AI adoption, stimulating innovation ecosystems like Bangalore’s deep tech hubs or Hyderabad’s T-Hub. 6. Sectoral Shifts and Alternative Employment Opportunities • Agriculture & Rural Economy: • Potential positive impact if educated, unemployed tech workers invest back into rural and agricultural innovation (precision farming, agritech startups, supply chain optimization), spurring rural economic revival. • Manufacturing Renaissance: • Government policy shifts could aggressively pursue manufacturing, emulating Vietnam’s successful transition, absorbing displaced IT-BPO workers into higher-tech manufacturing. • Creative Economy & Entertainment Sector: • Increased focus on creative industries (film, animation, gaming, content creation) with AI augmentation (generative AI in media production), leveraging India’s cultural exports like Bollywood and gaming studios. Proactive Strategic Solutions (Anticipating your needs): • Massive Re-skilling Initiative: • Establish national AI and emerging-tech universities and specialized boot camps in partnership with leading global tech companies (e.g., Apple, Google, Microsoft). • Example model: Israel’s “Technological Reskilling Initiative,” offering rapid certification courses. • Special Economic Zones (SEZs) for Advanced AI Industries: • Incentivize global companies to set up R&D centers, high-end AI application labs, quantum computing facilities, etc., creating high-value employment rapidly. • Universal Basic Income (UBI): • Temporary pilot programs (like Finland’s model) to stabilize displaced workers during transition periods. • Aggressive Venture Capital and Investment Climate: • Policy incentives and tax breaks for investments into new-age startups and innovation hubs, accelerating transitions into emerging sectors. Sources for Figures and Further Reading: • NASSCOM IT-BPO Industry Report 2024 • World Bank - India Economic Update • McKinsey Global Institute - AI and Automation Reports Thought-Provoking Follow-Up Questions: Q1: How would an aggressive adoption of AI-driven automation reshape India’s geopolitical role, especially concerning global tech rivalry between the US and China? Q2: Could the Indian government’s push towards advanced manufacturing and semiconductor industries realistically replace lost IT-BPO economic outputs within a decade? Q3: How might aggressive automation in India influence patterns of internal migration, urbanization trends, and urban infrastructure investment in the coming decades? Q4: Would a major disruption from AI automation potentially trigger social and political reforms in India’s historically rigid education and employment systems? Q5: Given India’s large informal economy, how might widespread AI-driven displacement of formal IT sector employment affect the informal sectors and small businesses across the country?

has anyone seen analysis/writing on the potential impact of AI automation on the economies of India, Philippines, etc that have a lot of outsourced IT, BPOs, etc? Imagine all the call centers, backoffice support for accounting, outsourced IT, etc etc. Seems like it might be a big deal from a global economic perspective, particular the balance of power between China and India. (And then, the global alliance counterbalancing China that includes India and many others)

@andrewchen From building GenAi apps for contact centers- I see it augmenting not replacing humans. Lots of need for human in the loop to validate AI summaries, insights, etc Shift from managing inputs raw data manipulation to managing AI generated outputs

Mason Barela (‘24,FL) • @CornellBaseball Leadoff single to start the inning. #SSF @CBU_FL

@johncutlefish Hmmm there’s already hundreds of dashboards and millions of data points readily available but rarely used. What exact and specific use cases are you talking about and how frequently do middle managers perform them?

Cam Smith, a freshman shortstop from @FSUBaseball will be a household name by the end of this season. Video from @brettpn

Hopefully we can be more human … plenty of specialists will also be displaced by AI