←
Logan650 posts
Logan avatar

Logan

@loganzev

building / tinkering prev | @thoughtfullab | @cornell |

◷ Joined August 2018▧ 72 Photos and videos
Logan avatar
Logan@loganzev·Nov 16

Excited to release The Trust Table. Been spending the last couple weeks learning how to use the new Tinker API, play with open source models and develop games for models to play and learn from. This is a personal benchmark I created as a research and product experiment. The goal was to learn how to fine-tune a model and explore a question I’ve been thinking about: do models know when they don’t know the answer? This is my first project of this kind, and it’s not a perfect study. The results are specific to this game, but I learned a lot from building it. Thank you to @thinkymachines and @tinkerapi for making the tools available to build and learn with!

0:06
Logan avatar
Logan@loganzev·11h

Jensen isn't coming back. Instead, he will become an advisor to Coreweave, Nebius, AMD, Intel, Reflection, Micron, TSMC...

Logan avatar
Logan@loganzev·20h

Google naming their personal agent "Googler" is gonna break this app

Luke Bousfield avatar
⟳ Logan retweeted
Luke Bousfield@LukeJBousfield·21h

Introducing Interact-0, the first in a new generation of always-on models. Interact-0 is a full-duplex speech model designed around human interaction. It is the only model that knows when to speak in groups, and can be active without barging in when it shouldn’t. We share our thesis, approach, and early results below. interact.inc/blog/interact-0…

2:11
Logan avatar
Logan@loganzev·Nov 16

Poetry

People make MCP sound so complicated, but isn't it basically just an API that tells AI agents how to use it?

brandon galang avatar
⟳ Logan retweeted
brandon galang@brandon_galang·Nov 16

cool project from my friend @loganzev "I don't know" Bench

Excited to release The Trust Table. Been spending the last couple weeks learning how to use the new Tinker API, play with open source models and develop games for models to play and learn from. This is a personal benchmark I created as a research and product experiment. The goal was to learn how to fine-tune a model and explore a question I’ve been thinking about: do models know when they don’t know the answer? This is my first project of this kind, and it’s not a perfect study. The results are specific to this game, but I learned a lot from building it. Thank you to @thinkymachines and @tinkerapi for making the tools available to build and learn with!

0:06
Logan avatar
Logan@loganzev·Nov 16

Can play the game live!

Post attachment

Excited to release The Trust Table. Been spending the last couple weeks learning how to use the new Tinker API, play with open source models and develop games for models to play and learn from. This is a personal benchmark I created as a research and product experiment. The goal was to learn how to fine-tune a model and explore a question I’ve been thinking about: do models know when they don’t know the answer? This is my first project of this kind, and it’s not a perfect study. The results are specific to this game, but I learned a lot from building it. Thank you to @thinkymachines and @tinkerapi for making the tools available to build and learn with!

0:06
Logan avatar
Logan@loganzev·Nov 16

Hold on. Can everyone just stop posting for a second so I can go through my bookmarks

Logan avatar
Logan@loganzev·Nov 16

throw back sundays

Today, we're releasing Ramp CLI to let agents manage your company's finances. 50+ tools across cards, bills, expenses, travel, and approvals. Fewer tokens than MCP, and comes with pre-built skills like receipt compliance and agentic purchasing.

0:30
Logan avatar
Logan@loganzev·Nov 13

Wish I ordered this… @imjaredz are sales popping today?

It's hard to stockpile a 90-day doomsday kit if you are like me and live in a tiny NYC apartment.. Well worry no longer! I put together a supply list optimized for under-the-bed storage apartmentdoomsdaykit.com/

0:03
Logan avatar
Logan@loganzev·Nov 11

UX: “Can a human use our product easily?” AXO: “Can an agent accomplish its user’s goal through our product?”

companies replicating their products as RL environments will come from everyone fascinating product implications in building the RL environment to steer agents in the optimized flow for your company implications from an agentic commerce pov as well

Logan avatar
Logan@loganzev·Nov 11

companies replicating their products as RL environments will come from everyone fascinating product implications in building the RL environment to steer agents in the optimized flow for your company implications from an agentic commerce pov as well

We just shipped AWS Emulator, which gives coding agents a local copy of AWS to test against. Early in my career, we built test environments like this by hand, one system at a time. Now, agents are writing code far faster than any team can check it in production. Matt Goldberg, a Senior Principal Engineer on our Developer Tools team, wanted to know whether agents could build and test those environments themselves. He gave @kirodotdev a single prompt, and about 15 minutes later it came back with a first version of an SQS emulator. Turing that into a robust solution took much more work Here’s what I think this means for engineers today: allthingsdistributed.com/202…

Logan avatar
Logan@loganzev·Nov 11

Wish people would resurface old bangers. Or somehow incorporate into the algo…

Jason Wei@_jasonwei16 Jul 2025

Becoming an RL diehard in the past year and thinking about RL for most of my waking hours inadvertently taught me an important lesson about how to live my own life. One of the big concepts in RL is that you always want to be “on-policy”: instead of mimicking other people’s successful trajectories, you should take your own actions and learn from the reward given by the environment. Obviously imitation learning is useful to bootstrap to nonzero pass rate initially, but once you can take reasonable trajectories, we generally avoid imitation learning because the best way to leverage the model’s own strengths (which are different from humans) is to only learn from its own trajectories. A well-accepted instantiation of this is that RL is a better way to train language models to solve math word problems compared to simple supervised finetuning on human-written chains of thought. Similarly in life, we first bootstrap ourselves via imitation learning (school), which is very reasonable. But even after I graduated school, I had a habit of studying how other people found success and trying to imitate them. Sometimes it worked, but eventually I realized that I would never surpass the full ability of someone else because they were playing to their strengths which I didn’t have. It could be anything from a researcher doing yolo runs more successfully than me because they built the codebase themselves and I didn’t, or a non-AI example would be a soccer player keeping ball possession by leveraging strength that I didn’t have. The lesson of doing RL on policy is that beating the teacher requires walking your own path and taking risks and rewards from the environment. For example, two things I enjoy more than the average researcher are (1) reading a lot of data, and (2) doing ablations to understand the effect of individual components in a system. Once when collecting a dataset, I spent a few days reading data and giving each human annotator personalized feedback, and after that the data turned out great and I gained valuable insight into the task I was trying to solve. Earlier this year I spent a month going back and ablating each of the decisions that I previously yolo’ed while working on deep research. It was a sizable amount of time spent, but through those experiments I learned unique lessons about what type of RL works well. Not only was leaning into my own passions more fulfilling, but I now feel like I’m on a path to carving a stronger niche for myself and my research. In short, imitation is good and you have to do it initially. But once you’re bootstrapped enough, if you want to beat the teacher you must do on-policy RL and play to your own strengths and weaknesses :)