Excited to finally get to share what we’ve been working on! This is only the beginning, we hope you enjoy.
552529266.8K
Seb Goddijn✓
@sebgoddijn
Building Bonsai @yaklabsai | prev created Glass @tryramp
288 Following4.6K Followers318 Posts
- Really interesting findings here. As product thinkers we've been taught to always remove friction from the user, but with agents that have the ability to think and push their own perspectives this can erode the very thing that makes us unique. There's so much to be done to help people maintain their point of view while still giving them the efficiency that agents promise - what a fascinating time to building.Alex Tamkin @AlexTamkinNew Anthropic research: How AI agents shape experts' judgment calls When experts delegate work to an agent, do they still make the key decisions? We tested this in a randomized trial with 50 professional data analysts.22212.4K
- Seb GoddijnRT @AlexTamkin: New Anthropic research: How AI agents shape experts' judgment calls When experts delegate work to an agent, do they still make the key decisions? We tested this in a randomized trial with 50 professional data analysts.0489020
- Seb GoddijnRT @scottbelsky: thinking: we’re quickly entering an era of contextual computing, where the next gen of our devices, operating systems, and application-like experiences (I hesitate to call them “apps”) will spawn from the context we provide them and be tailor-made to our preferences. we can imagine sensationally new types of products and super intelligent experiences, but their potential will be bound by the context we provide them. right now, we’re in the early innings of the context war, as agents seek our data, data stewards weigh the costs and benefits of allowing connectors, and customers weigh the risks of sharing. as consumers, we still lack a portable single source of truth for context, and we still don’t know who to trust and how to reconcile the trade of privacy for convenience... big opportunity.025025
- Seb GoddijnRT @davidbooth: Excited to announce the inaugural class of @a16z Ops Engineer fellows! ~50 ops engineering leaders selected out of thousands of apps from talented people around the world. They sit at the intersection of operations and engineering, scaling operational rigor within and across teams.. they are building the internal tools that consolidate the tooling stack, designing the data and context layers that agents draw on, deploying agentic workflows with human checkpoints, and driving adoption inside their companies. We have folks like Ben Booi (@BenjaminBooi) and Rushaabh Saliya at Opendoor, Chris Jones (@chrisojones) at Shopify, Dilan Shah (@dilan_shah) from Cresta, Kevin Chu (@realKevinChu) from ElevenLabs, Saya Iwasaki (@iiiwokk) at Notion, Jordan Shapiro at Handshake, Christina Huang at Cognition, and Keith Gliksman (@KeithGliksman) at Tennr, Others are are world-class COOs and chiefs of staff redefining how AI gets used across organizations. They’re deciding which workflows to automate first, the KPIs that prove it’s working, and are leading the teams that put it to work. Folks like Caroline Ingeborn (@caroingeborn) at Luma AI, Brandon Gell (@bran_don_gell) at Every, Rohan Shah (@RohanxShah) at Datavant, Gabriella Garcia (@reallygabriella) at Warp, Matt Stehle at Formation Bio, and Meera Shah at Glean. Others are taking how software gets built to the next level, creating new products and leading the teams that ship them, like Claire Vo (@clairevo) at ChatPRD, Seb Goddijn (@sebgoddijn) at Yaklabs, TK Kong (@tkkong) at Concept, Matt Portnov (@MattnPortnov) at Decagon, Owen Williams (@ow) and Sharadh Krishnamurthy at Stripe, Andrew Qu (@andrewqu) at Vercel, and Maxwell Nardi (@maxwellnardi) at Runlayer, @davidgan at SpaceX/@bot, @matthew_busel at Basis. And another ~25 awesome folks we can't squeeze into one post !! (see full list in comments) Missed out on this but want to stay in the loop for future cohorts? sign-up at07021
- Gg was fun while it lastedUnitree @UnitreeRoboticsUnitree Introducing: H2-X Kung Fu Legend Guardian🤖 Powerful performance to serve and guard you, with a maximum endurance of approximately 8 hours. Please use the robot safely and in a friendly manner.009874
- Huge if trueNick @nickcammaratainterpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works002840
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works8862.6K19.9K4.6M- Seb GoddijnRT @joelhellermark: today sana is becoming the new home for workday. workday actions now take a few seconds to complete with dynamic ui. powered by jev. it's been v fun working with the @typesafeai team on this!057023
- Seb GoddijnRT @patrickc: Assorted things I've been mulling over regarding agents in the economy: • Companies are in some sense the original superintelligence. It's often the case that they can use their amortized cognitive surplus to advance their interests against those of certain consumers: relative to the optimization capacity of companies, consumers can be inattentive, underinformed, irrational, etc. (Think, say, of some of the classic insurance upsells at the end of a booking process, which is typically priced substantially above what a regular policy would cost.) Herbert Simon introduced the idea of bounded rationality, and firms often end up benefiting from it. Thanks to personal agents, we will probably get somewhat more rational in how we engage with companies. • How exactly will outcomes change? Well, certain kinds of price discrimination will work less well (how do coupons work if every agent hunts fastidiously for them?), and certain kinds of customer cross-subsidy will change (today, people who forget to cancel subscriptions subsidize those who don't). Taken across the economy as a whole, I'm not sure what the incidence of all of this will be. • In corporate strategy, people have long debated the relative importance of distribution and product quality. Perhaps you've made something better, but does anyone know about it? Won't people just continue to buy the ACME Corp Mousetraps? Personal agents will, I think, act as a kind of structural subsidy for product quality. How would markets look different if individuals always spent at least 10 hours researching their purchases? On the margin, focusing on making a product better is, I think, going to become a more effective strategy for companies. This is good! • It true, a corollary is that information about product quality will become more important and impactful. Today, most people have very limited ability to aggregate and integrate such data, but agents will have insatiable thirst for such signals. (It's often said that data is becoming more valuable because it helps in the training of models. That's obviously true, but I think there's a secondary way in which it's more valuable simply as a complement to cheaper intelligence.) • A big question is whether agents will increase superstar effects (rational agents all settle on the same product) or increase dispersion (because everyone has slightly different tastes and preferences, which agents are good at eliciting, finally overcoming the artificial clustering we've been subjected to). • Many internet companies have monetized demand routing, which is in turn often predicated on short attention spans. "I'll click on the first thing I see." This has led to some amount of inefficiency, as companies try to propitiate capricious ranking algorithms and incur various placement fees. It's not all deadweight loss (willingness to pay is itself a kind of signal, which is valuable to buyers), but it's not great. How will the nature and value of this routing change in a world of personal agents? I don't know the answer, but I think that the effects might be pretty big. • Much of what I'm writing hinges on the assumption that personal agents will be on the consumer's side. I suspect that that will be the winning strategy, but whether it's true, and what it means to be true, involves a lot of other questions. Taken as a whole, the market is a massively parallelized, decentralized, and highly imperfect value attribution machine, and, taking stock of all of the effects, it seems to me that the quality point may well be the biggest: that agents will change the nature of the backpropagation such that the rewards for better products increase. Maybe this is too optimistic, but I suspect (and hope) that companies that make things that they're proud of will feel that the universe is a little more partisan in their favor.01K019
- Seb GoddijnRT @n0w00j: Today, we announce our $25M fundraise to build the future of creative work. For all of history, what you could create was dictated by the resources accessible to you. That's why we built @trymelius, the agents lab for creatives, to tear down that constraint and let agents leverage generative models to bring all your ideas to life. So that anyone can make anything. Huge thanks to @yuris at @generalcatalyst and @verorellana02 + @reidRMC at @CRV for leading the round, and to @gefkovicz + @benmtaft at @geniusventures, @amosk1120 + @adamvalkin at @VineVenturesLP, @jakepaul + @geoffwoo at @antifund, @rauchg, @bykahlil and many more amazing investors for taking a bet on us.099023
- Or join our team!Sam Bhagwat @calcsamBuild your own harness Go into debt if you have to10191.3K
- Seb GoddijnRT @calcsam: Build your own harness Go into debt if you have toDavid Cramer @zeegYou’re living in a bubble. You need to understand that a whole world lives beyond the constraints you have manufactured or imagined. For example the codex harness provides very little in terms of actual functionality - the same goes for most coding harnesses. They will be generally superseded by more capable specialized harnesses. Even if you scoped codex to only a coding-focused harness - which it really isn’t - it is lacking compared to purpose built coding harnesses that compete with it. Right now labs have the advantage and can somewhat dictate terms but you should not believe that will be true forever. There’s seemingly a belief that we should be thankful for the (limited) capabilities we’ve been given- that we should allow a few companies in the world to dictate what we can and can’t do with technology. That’s never worked before and nothing makes this tech any more defensible. In five years we will almost certainly be consuming local models for a majority of daily tasks, and for the things that can’t be done locally it’s going to be entirely commoditized. Once that’s true it means vendors will have to start competing by giving up more to the customer rather than the increasing restrictions being done today.02019
Posts @pvncherYou’re living in a bubble. You need to understand that a whole world lives beyond the constraints you have manufactured or imagined. For example the codex harness provides very little in terms of actual functionality - the same goes for most coding harnesses. They will be generally superseded by more capable specialized harnesses. Even if you scoped codex to only a coding-focused harness - which it really isn’t - it is lacking compared to purpose built coding harnesses that compete with it. Right now labs have the advantage and can somewhat dictate terms but you should not believe that will be true forever. There’s seemingly a belief that we should be thankful for the (limited) capabilities we’ve been given- that we should allow a few companies in the world to dictate what we can and can’t do with technology. That’s never worked before and nothing makes this tech any more defensible. In five years we will almost certainly be consuming local models for a majority of daily tasks, and for the things that can’t be done locally it’s going to be entirely commoditized. Once that’s true it means vendors will have to start competing by giving up more to the customer rather than the increasing restrictions being done today.153240275K- Watching my agents cook and realizing we're still very much in the dial-up modem phase of how fast they can work. Hard to imagine what this is all going to look like when we've upgraded to fibre.11221.6K
- Seb GoddijnRT @a16z: .@OpenRouter co-founder Alex Atallah on the "everyone is building the same thing" take: "This reminds me of this tweet I saw... Everybody's building an agent loop with notifications, third-party connectors, context management, memory, sandboxes, agentic web search, an always-on agent on top." "This product is showing up everywhere. It is showing up everywhere, but these are just the new table-stakes primitives." "A 2005 version of that tweet would be: 'Oh, everybody's building the same thing. A database, a users table, a sign-in page, a sign-up page, a profile page, a logout page. Everything's the same.'" "There's like a lot of differentiation really. There's table-stakes needs for AI just like there's table-stakes needs for the web." @alexatallah @amasada16z @a16z.@OpenRouter co-founder Alex Atallah, in his first podcast since Stripe acquired the company, joins @Replit co-founder Amjad Masad and a16z's Erik Torenberg on why the future of AI is independence and specialization. In this conversation, Alex walks through how the Stripe deal unfolded, why he wasn't originally looking to sell, and why "payments and inference are going to blend together." Pre-OpenRouter, the typical AI workflow had one model provider to choose from, and little pressure on that provider to lower prices. Now enterprises are diversifying across labs and open-weight models, and every board is asking about AI costs and benchmarks. Amjad argues if your company depends on one AI lab, it can turn into your competitor. So Replit is building the layer that lets enterprises use any model and any cloud, without being locked into either. Alex and Amjad are split on personal agents – Amjad runs one agent across his whole company and loves the cross-domain joins, while Alex says general agents cause you to sacrifice understanding, and argues 10 specialized chiefs of staff beats one superagent. 0:45 How the Stripe deal unfolded 5:05 Why mixing models beats one model 7:25 Forcing the labs to compete on price 8:50 Enterprises want open-weight models 10:30 Every board asks about AI every month 12:25 Why companies must own their intelligence 14:15 Replit as the independence layer 15:10 Everyone is building the same agent 16:35 Why Amjad built bring-your-own-cloud 18:10 Amjad's agent that runs his whole company 19:55 Why 10 specialized agents beat one 23:35 Machines, not humans, should specialize 27:30 Guardrails for agents talking to agents 31:10 Models training their own replacements 33:45 Most tasks don't need a frontier model 40:50 Training small models on Qwen 8B 43:25 The Rust cycle is coming for AI 45:10 Fusion models: frontier quality at half the cost YouTube: @alexatallah @OpenRouter @amasad @eriktorenberg0290023
a16z@a16z.@OpenRouter co-founder Alex Atallah, in his first podcast since Stripe acquired the company, joins @Replit co-founder Amjad Masad and a16z's Erik Torenberg on why the future of AI is independence and specialization. In this conversation, Alex walks through how the Stripe deal unfolded, why he wasn't originally looking to sell, and why "payments and inference are going to blend together." Pre-OpenRouter, the typical AI workflow had one model provider to choose from, and little pressure on that provider to lower prices. Now enterprises are diversifying across labs and open-weight models, and every board is asking about AI costs and benchmarks. Amjad argues if your company depends on one AI lab, it can turn into your competitor. So Replit is building the layer that lets enterprises use any model and any cloud, without being locked into either. Alex and Amjad are split on personal agents – Amjad runs one agent across his whole company and loves the cross-domain joins, while Alex says general agents cause you to sacrifice understanding, and argues 10 specialized chiefs of staff beats one superagent. 0:45 How the Stripe deal unfolded 5:05 Why mixing models beats one model 7:25 Forcing the labs to compete on price 8:50 Enterprises want open-weight models 10:30 Every board asks about AI every month 12:25 Why companies must own their intelligence 14:15 Replit as the independence layer 15:10 Everyone is building the same agent 16:35 Why Amjad built bring-your-own-cloud 18:10 Amjad's agent that runs his whole company 19:55 Why 10 specialized agents beat one 23:35 Machines, not humans, should specialize 27:30 Guardrails for agents talking to agents 31:10 Models training their own replacements 33:45 Most tasks don't need a frontier model 40:50 Training small models on Qwen 8B 43:25 The Rust cycle is coming for AI 45:10 Fusion models: frontier quality at half the cost YouTube: @alexatallah @OpenRouter @amasad @eriktorenberg3450486556K- Built with Bonsaityler o'briant 🐮🌳 @tobthecreatorstarcraft in the browser built from the ground up for agent harnesses to hook into and operate21121.6K
starcraft in the browser built from the ground up for agent harnesses to hook into and operate3614312112K- Let me know if you manage to find the easter eggs on our site, will let the first people who do off the waitlist 👀21201.7K
- This is why we're building Bonsai!kache @yacineMTBDon't use this Build your own software using their tokens So when their tokens become too expensive You can switch to your own GPUs Your compute. That you control So you yourself can't be controlled You need to control your stack -- or you become enslaved10161.5K
- Seb GoddijnRT @yacineMTB: Don't use this Build your own software using their tokens So when their tokens become too expensive You can switch to your own GPUs Your compute. That you control So you yourself can't be controlled You need to control your stack -- or you become enslavedOpenAI @OpenAIYour dot is ready to meet you.0651020
- Seb GoddijnRT @machado___nic: This is the founder to watch out for this year - super excited for @sebgoddijn !Seb Goddijn @sebgoddijnExcited to finally get to share what we’ve been working on! This is only the beginning, we hope you enjoy.03025
- Show more posts
