Eric Litman

6.1K posts

Eric Litman banner
Eric Litman

Eric Litman

@ericlitman

Founder @healthspanners, @aescape Avid health optimizer Serial optimist

New York City Katılım Nisan 2007
906 Takip Edilen4.2K Takipçiler
Sabitlenmiş Tweet
Eric Litman
Eric Litman@ericlitman·
Speechless.
Eric Litman tweet media
English
6
4
46
4.3K
Eric Litman retweetledi
Y Combinator
Y Combinator@ycombinator·
Cancer kills because it's caught late. Adialante is changing that by making mobile MRI accessible — dropping its costs to hundreds per scan and wait times to hours. Annual cancer screening will be the norm. Congrats on the launch, @ET_adialante & @ManW_dePlan! ycombinator.com/launches/QLh-a…
English
56
105
991
117.1K
Eric Litman retweetledi
Jonas Geiping
Jonas Geiping@jonasgeiping·
We’re training models wrong and it’s due to chatGPT. Even the modern coding agents used daily still use message-based exchanges: They send messages to users, to themselves (CoT) and to tools, and receive messages in turn. This bottlenecks even very intelligent agents to a single stream. The models cannot read while writing, cannot act while thinking and cannot think while processing information. In our new paper, see below, we discuss LLMs with parallel streams. We show that multi-stream LLMs can … 🔵Be created by instruction-tuning for the stream format 🔵Simplify user and tool use UX removing many pain points with agents and chat models (such as having to interrupt the model to get a word in) 🔵Multi-Stream LLMs are fast, they can predict+read tokens in all streams in parallel in each forward pass, improving latency 🔵 LLMs with multiple streams have an easier time encoding a separation of concerns, improving security 🔵 LLMs with many internal streams provide a legible form of parallel/cont. reasoning. Even if the main CoT stream is accidentally pressured or too focused on a particular task to voice concerns, other internal streams can subvocalize concerns that would otherwise not be verbalized. Does this sound related to a recent thinky post :) - Yes, but I don’t feel so bad about being outshipped with such a cool report on their side by 23 hours. I’ll link a 2nd thread below with a more direct comparison. I actually think both are complementary in interesting ways.
GIF
English
41
166
1.3K
148.4K
Eric Litman retweetledi
Genspark
Genspark@genspark_ai·
🎁 Introducing GenClipboard. Copy anything. Paste it anytime. Totally free. We've been using it inside Genspark for months. Today, we're sharing it with everyone. Everything you copy, kept and searchable: - Text, links, passwords, and code - Images and screenshots - Scroll captures and screen recordings Never lose a thing. Grab it free → genclipboard.ai or genspark.ai/download
English
21
15
151
33.9K
Eric Litman
Eric Litman@ericlitman·
Nice little developer experience tip: have your agent write a post-work summary in HTML, publish it to here.now, then slack/message you the link. No signup/api key needed, URLs are random and expire 24 hours after publishing if you post anonymously.
English
0
0
2
36
Alex Lieberman
Alex Lieberman@businessbarista·
I want to start an AI community for executives. This will be a space for people to share killer use cases, agentic workflows/agents, post-AI org structure, AI governance, AI training/enablement, change management, and more. Comment “AI-native” if you want to join.
English
1.8K
33
1.1K
182.2K
Eric Litman retweetledi
Charlie Harris
Charlie Harris@charlieharris01·
NEW: today OpenBind ‘comes out of stealth’ so to speak with their first data dump of ~900 novel protein-ligand structures - most with paired affinities This represents a meaningful %-age increase in all of humanities P-L data in the PDB collected in the last 50 years More👇
Charlie Harris tweet media
English
6
83
355
43.9K
Kishan Bagaria
Kishan Bagaria@KishanBagaria·
who wants an imessage cli that your agents can use uses your existing apple id/number, doesn't require disabling SIP, 95% feature parity on tahoe (reacts/unsends etc.), purely native swift...
English
29
3
195
28.3K
Eric Litman
Eric Litman@ericlitman·
@thsottiaux @gao_zibo Please make remote mobile from your workstation a first class citizen, including spawning new sessions from mobile. 🙏
English
0
0
3
712
Tibo
Tibo@thsottiaux·
@gao_zibo All of this and more is coming
English
214
83
3.3K
492.1K
Zibo Gao
Zibo Gao@gao_zibo·
codex mac app is winning SO HARD. just need: - native editor - iOS app - full browser - openclaw then it might be the home default app
English
44
23
1.6K
126.8K
Eric Litman retweetledi
Prash Singh
Prash Singh@prash_singh·
I think structural glycobiology is entering a breakout phase. In the next few years, high-resolution cryoEM, AI-guided glycan modeling, and structural glycomics will challenge the protein-centric view of molecular biology by showing that glycans are not just decorations, but structural and functional determinants of biological machines. A new paper in journal Science has revealed structural glycans using cryo-EM analysis of tubular mastigonemes.
Prash Singh tweet media
Oak Hill, TN 🇺🇸 English
9
36
166
8.8K
Eric Litman retweetledi
Chris Tate
Chris Tate@ctatedev·
Introducing AI CLI Generate images, video, and text from your terminal. Pipe them together. Works with any agent. ai image "sunset" | ai video "animate" → Hundreds of models → Multi-model comparison → Inline previews, no native deps → AI SDK + AI Gateway
English
77
62
1K
60.7K
Eric Litman retweetledi
fks
fks@FredKSchott·
Introducing Flue — The First Agent Harness Framework Flue is a TypeScript framework for building the next generation of agents, designed around a built-in agent harness. Flue is like Claude Code, but 100% headless and programmable. There's no baked in assumption like requiring a human operator to function. No TUI. No GUI. Just TypeScript. But using Flue feels like using Claude Code. The agents you build act autonomously to solve problems and complete tasks. They require very little code to run. Most of the "logic" lives in Markdown: skills and context and AGENTS.md. Flue is like Astro or Next.js for agents (not surprising, given my background 🙃). It's not another AI SDK. It's a proper runtime-agnostic framework. Write once, build, and deploy your agents anywhere (Node.js, Cloudflare, GitHub Actions, GitLab CI/CD, etc). We originally built Flue to power AI workflows inside of the Astro GitHub repo. But then @_bgiori got his hands on it, and we realized that every agent needs a framework like Flue, not just us. Check it out! It's early, but I'm curious to hear what people think. Are agents ready for their library -> framework moment?
fks tweet media
English
182
341
3.7K
737.6K
Eric Litman
Eric Litman@ericlitman·
People who never floss rejoicing
Anish Moonka@anishmoonka

Your jaw has the parts to grow a third set of teeth. They never finished forming. A protein in your body kept them locked away since before you were born. Japan's new drug blocks that protein. The lock comes off. Those buried tooth parts wake up and grow into real teeth. In 2018, this worked on mice. It worked again on ferrets. The team picked ferrets because, like humans, ferrets grow two sets of teeth in their lifetime. Rats and mice don't. Human trials started at Kyoto University in late 2024. Thirty men, aged 30 to 64, each with at least one missing molar, are receiving injections. This first round only tests safety. Whether it grows teeth in real people is still unknown. That data is years away. The first patients to be treated will be young children, ages 2 to 7, born missing 6 or more permanent teeth. This is a rare birth defect affecting about 1 in 1,000 people. Trials in those kids run through 2027. The next round through 2029. Earliest public sale: 2030. For adults losing teeth to cavities, accidents, or old age, the wait is longer. Toregem itself admits dentures and implants will stay the standard answer for years. A single implant in America costs $3,000 to $6,000, and the global implant market was worth $5.5 billion in 2025. So the headline oversells things. Nobody is replacing implants this decade. But the Japanese dentist behind the drug spent nearly 30 years working on this. He found an ancient genetic switch our bodies stopped flipping long ago, and built a way to flip it back on.

English
0
0
0
91