Matt Pocock
@mattpocockuk ·
Debating just straight-up banning useState in my React apps
Push the agent into the black hole of success
Back
AI posts
AI posts
People and companies shaping AI. Filter your watched accounts, catch up on recent posts, or find the most liked and viewed.
Compiled by the Toolstash team · Updated
209 watched accounts · 2978 matching posts · Showing up to 3,000 recent stored posts. Counts are snapshots, not live X totals. This page refreshes every minute while visible. Last collected .
dax@thdxr ·
with supply chain attacks becoming a bigger problem AUR really has to become more sophisticated or get replaced
it's impossible to securely publish packages there
Mia@MiaAI_lab ·
64 GB DDR5 prices 💀
elvis@omarsar0 ·
Great paper from Amazon and colleagues on self-improving multi-agent systems.
Episodic memory for agents is so underrated.
But I am starting to see lots of good applications as frontier models improve.
This paper is the latest example.
They built a system that has three parts, all run by the same LLM. A controller plans each task and runs it one step at a time, choosing which sub-agent and which skills to use at each step. Sub-agents start as a generalist, and each specialist inherits the generalist's prompt plus its own role-specific method. Skills are short procedures, such as algorithms or pitfall checklists.
EMMA treats the controller's routing memory, the agent prompts, and the skills as episodic memory that improves from failures. After a failed task, a reflector decides which of the three owns the fix and proposes one edit there. Guards keep every accepted edit scoped, incremental, and bounded.
EMMA beats ACE, GEPA, EvoMAS, and ADAS on KramaBench, AppWorld, and BBEH, by up to 32.5% over the strongest baseline, and uses 17 to 38% fewer training executions.
https://arxiv.org/abs/2610.35966
Chat with Paper: https://academy.dair.ai/papers/emma-structured-episodic-memory-for-multi-agent-workflow-synthesis-2610.35966
Santiago@svpino ·
People are now writing code faster than they can roll it out to their users.
You need a plan for rolling out new features and updates. This is not optional anymore.
I've made so many mistakes deploying updates to software I've built that I could write an encyclopedia about everything you should and shouldn't do.
One of the most important lessons I've learned:
Never rush new code in front of all your users, especially now that agents generate so much of our code.
You need a way to decide what goes live, who gets it first, and when it's ready for more people.
This is how I usually implement this:
1. I have a new feature I want to release. I put it behind a switch in the code so I can turn it on or off. We call this "feature flags."
2. After I test the code, I deploy it with the flag off. Nobody has access to it at first. I want the deployment and the feature to become two separate decisions.
3. I then turn the flag on for a small group of users while everyone else keeps using the existing version.
4. I monitor what happens with the feature. Does it work as I expected? Are there any errors?
5. I gradually let more people use the new feature until I'm comfortable removing the flag.
6. If something breaks, I can turn the flag off for everyone and stop the problem until I fix it.
I call these gradual rollouts "canary releases". They're easy to implement with feature flags.
Feature flags don't replace code reviews or testing. They just give you another layer of control.
You don't have to build a feature flags system yourself. @LaunchDarkly manages the whole thing for you:
• Add flags to your code • Choose who gets the feature • Increase the group over time • Turn flags on or off without redeploying • Implement guarded rollouts to watch metrics during a release • Use automatic rollbacks
Here is a link to get started: https://fandf.co/4yWcjSq
Agentic coding is amazing, but it's only worth it if you can confidently put working software in front of your users.
Thanks to the LaunchDarkly team for partnering with me on this post.
Nathan Lambert@natolambert ·
Private benchmarks often show open models are further behind, but the problem with private benchmarks is you don’t have the community to squash the inevitable bugs for you. I'm 50/50 on if I think private or open-source is the best approach.
Aravind Srinivas@AravSrinivas ·
Fun project on Perplexity Computer: Asked it to design a GTA V mission where you vibecode GTA VI from an in-game phone while the devs call the cops on you for shipping GTA VI before them.
It went through the FiveM docs (natives, ped models, server convars, the limits of the in-game browser) and built the mission as a FiveM resource in Lua. Then it built an MCP bridge, a small local Node service that signs in to the Perplexity Computer MCP server with OAuth and turns your in-game prompt into a real Computer task.
The phone streams Computer's steps live during the chase, you answer its questions and approvals while driving, and you ship the build by losing the cops at the airport hangars.
For the voices, Computer rented a cloud GPU and ran Qwen3-TTS locally on it, with no TTS API, to voice every line of dialogue.
Derya Unutmaz, MD@DeryaTR_ ·
This is a very exciting potential new treatment for food allergies! But to appreciate just how remarkable this development is, let me share a personal story about Xolair, the anti-IgE antibody currently used to treat allergies, and how painfully slow biomedical progress has been until now. I believe AI is about to change this dramatically!
Back in 1989, 37 years ago, I was a visiting medical student as an intern at Ciba-Geigy immunology laboratories (which later became part of Novartis) in Basel, Switzerland. In the immunology department where I was working, one of the scientists, Christoph Heusser, had proposed developing antibodies against IgE, the molecule responsible for triggering allergic reactions, back in 1986!
Around the same time, scientists at a small biotech company called Tanox had independently developed a promising anti-IgE antibody. Ciba-Geigy and Tanox subsequently formed a partnership in 1990 to advance this approach.
I still remember the excitement surrounding this research as vividly as if it were yesterday! Imagining the possibility of treating allergies by targeting a single molecule responsible for triggering the entire allergic response was extremely novel back than. I was fortunate enough to witness the early development of this revolutionary idea firsthand, and it was incredibly exciting!
But here is where the story becomes rather astonishing.
Genentech subsequently developed a similar antibody in 1993, and the three companies eventually joined forces. Their collaboration led to Xolair (omalizumab), which finally received FDA approval in 2003, 17 years after the original concept! And that approval was initially for allergic asthma. It took another 21 years, until 2024, for Xolair to receive approval specifically for food allergies!
Think about that. Almost 40 years after those original discoveries, Xolair remains the only FDA-approved anti-IgE antibody for food allergies. That is how painfully slow the traditional process of developing new medicines has been!
Now compare that timeline with what Claude and Divergence Labs have accomplished in approximately ONE MONTH!
Claude generated roughly 35,000 antibody designs, helping identify promising candidates that could potentially remove IgE already attached to immune cells. This could be a major advance over Xolair, which primarily neutralizes free IgE. Some of these new antibody designs already performed better than Xolair in specific laboratory tests!
Of course, these are still early experimental results. The complete therapeutic antibody needs to be developed, validated, and eventually tested in clinical trials.
But consider the implications!
We are witnessing the beginnings of a fundamental transformation in biomedical research. As AI intelligence continues to advance exponentially, combined with automated laboratories, virtual cells, and eventually patient digital twins, I believe we will compress decades of drug discovery into months or even weeks!
Clinical trials and regulatory approval will also become much faster as AI improves our ability to predict efficacy, toxicity, and treatment responses.
My prediction is that instead of waiting decades for individual breakthrough medicines, we will eventually be developing hundreds, perhaps thousands, of new treatments in parallel, within just a few years!
Having personally witnessed the beginnings of anti-IgE antibody development nearly four decades ago, and now seeing AI begin to revolutionize that very same field, makes this moment extraordinarily exciting for me.
I have been waiting for this transformation for most of my scientific career. And I believe we are finally entering the era when the pace of medical discovery will accelerate beyond anything we have experienced in human history!
Daniel San@dani_avila7 ·
Firecrawl MCP is now available on http://aitmpl.com
You can use it with Claude Code to scrape websites, crawl entire sites, search the web, and extract content as Markdown or structured JSON
It includes tools like scrape, crawl, map, and search
Claude Code can call them directly when needed
Install it with one command:
npx claude-code-templates@latest --mcp devtools/firecrawl
You’ll need a Firecrawl API key
Maziyar PANAHI@MaziyarPanahi ·
I trained a small open model overnight to say "not sure, ask a doctor" 🔥
it answers on its own only when it's 90%+ sure, and hands everything else to a human
when it answered alone, its mistakes dropped from 46 to 13
which decisions would you let an AI make alone?
Vox@Voxyz_ai ·
If you still think AI video 𝗹𝗼𝗼𝗸𝘀 𝗳𝗮𝗸𝗲, look at the bottom half.
That's FLUX 3 Max, now live in Arcads. The realism is insane..😭 You'd swear it was real footage.
It's also up to 𝟮𝟮𝘅 𝗳𝗮𝘀𝘁𝗲𝗿 than other leading video models at the same quality. A 10-second clip comes back in about 12 seconds.
At that speed, you can try several camera moves on the same shot and keep the best one. Call the move by name in your prompt:
→ dolly zoom: the person stays the same size while the background stretches away or closes in → rack focus: focus shifts from the foreground to the background → FPV drone shot: the camera rushes forward like a drone → whip pan: the camera snaps sideways and blurs into the next shot
When you name one, add the seconds and the speed, like "dolly in, 3 seconds, slowly toward the person."
- Nathan Lambert
@natolambert ·
Open models' demise has been greatly exaggerated, but the previous AA index did flatter them. As an industry we need more specific intelligence indices, as LLMs are used in vastly different tasks.
My meta-review on the benchmarking industry. https://www.interconnects.ai/p/artificial-analysis-v5-and-the-benchmarkers
Marc Lou@marclou ·
And that, ladies and gentlemen, is the end of UI for SaaS
Romain Huet@romainhuet ·
Codex on the iPhone Duo is 🤩
Gergely Orosz@GergelyOrosz ·
I'm starting to sense a divide in the tech industry:
- People thriving on autonomy who are reinventing how they work and what tools they use with AI: LOTS of work, but they're enjoying it and getting very efficient
- People used to being mentored / trained / or simply told what to do and how. Frustrated with the lack of guidance from management on what to do with AI; also frustrated by seeing some of their peers thriving; increasingly bitter about AI and the state of the industry, as a whole
Neither group seems to be aware that there's another group, or have empathy for the other group
- Santiago
@svpino ·
Everyone should focus on automating code reviews.
Right now, agents can write a virtually infinite amount of code, but it's for nothing if it doesn't work.
I see people clinging to "manually reviewing the code" as the only way forward. I think this is a mistake and a major bottleneck we all need to get rid of.
You want people to focus their time on things only people can do.
You want agents to focus on everything else.
There's no one-size-fits-all solution here, but you should spend as much time as possible building a process that removes the review bottleneck.
- elvis
@omarsar0 ·
Yes, the coding interview is absolutely dead!
It should have been gone a long time ago. With coding agents this good, we can now focus on hiring people with high agency, taste, judgment, empathy, and principled thinking.
This also gives junior engineers a fair chance. I am often surprised by how better equipped they are, how fast they move, and their creativity and ambition. You need all those qualities in this brave new world.
I recently gave a talk at a university, and I suggested to senior students that they look at data (understand and analyze it) and pick a domain they are passionate about. Then build a prototype that tries to solve a problem and share it publicly (X, GitHub, YouTube, Kaggle, etc.). The first project might not get any attention, but if you do this often, you will eventually find someone, or hopefully a few, in the industry who care as much as you do about the problem you are trying to solve. Show that desire and hunger. It matters so much today.
If you are just starting your career, don't pay attention to all the noise (e.g., AI taking away jobs, etc.). Keep building and shipping. Master your fundamentals (systems thinking goes a long way today). And stay hungry.
Ethan Mollick@emollick ·
There has been a bunch of really interesting experiments with activating individual neurons in open AI models, locking them into particular personas.
Here historian @ResObscura tries the same trick with a model trained only on data before 1930, and the results are delightful.
Theo - t3.gg@theo ·
I should clarify: this is over the internet, not via computer use.
If I turned off my laptop, I can still control my other machines via my Grok Bot on my phone.
@levelsio@levelsio ·
Everything I do runs on my VPS servers
The only interface is Termius SSH and then Claude Code on the server
All my businesses but also my health stuff, calories, sleep etc. all my data is pulled into there
Then the output is either chat responses from Claude Code on the server or websites it builds
So I can ask "did magnesium last night improve my sleep" and it pulls my sleep from WHOOP, nutrition from my food tracker, and even bedroom temperature and air quality data to check confounding factors etc
All server side!
kache@yacineMTB ·
Deepseek flash 1017 is genuinely a better model than any of the garbage that OpenAI is peddling
Peter Gostev@petergostev ·
This is a little chart I made 2 years ago (before GPT-5 was launched).
GPT-5 era muddied the waters a bit with heavy RL, but we are definitely following this cycle with GPT-6 now.
Dean W. Ball@deanwball ·
This is the first time an Artificial Analysis ranking has even roughly approximated my own subjective rankings of models.
Gabriel Chua@gabrielchua ·
"benefits all means intelligence for all"
Pavel Rabtsevich@p_rabtsevich ·
2 subs and both finished, nice limit reduction. from the previous last week where we had it unilimited, now even 2 x20 is not enough
anthropic saw me paying for 2 and thought "why stop there" 😀
- Mia
@MiaAI_lab ·
Important updates and fixes have been pushed to DeepSeek V4.1 Flash for 4x DGX Sparks ⚡️
This update includes 7 community PRs!
Performance - Chats with images: resending a 35-image chat dropped from 20 s to 1 s (20x faster) - No more waiting: a short question asked during a long 51k-token prompt now answers in 0.3 s instead of ~13 s - CPU use per machine dropped from ~310% to ~0.2% (about 12 CPU cores freed) when on idle
More reliable - Long prompts no longer time out clients (a keep-alive signal every 15 s) - Safer start/stop scripts - The test tools can’t report a false “pass” anymore
Also, /metrics now shows how many prompt tokens came from the cache (prompt_tokens_cached_total), so dashboards can tell cache hits from real prefill work
Thanks to @easthambuilds, @krunkosaurus, @uchkw, Manuel (manuel1618), and SvangenStudios, plus upstream TensorFold work by @jayleaton, @ashxhart and @BobClawblaw 🙏
Get it here: https://mia-ai.net/models/DeepSeek-V4.1-Flash-1017-4x-DGX-Sparks-TensorFold
- @levelsio
@levelsio ·
+16 min REM if you compare to last 30 days
But again only directional, not proven yet until it keeps happening!
- Theo - t3.gg
@theo ·
Day 29/
You can now control your whole fleet through a single MCP server in T3 Code. Here's me spinning up 8 threads on different machines via Grok Bot.
- Marc Lou
@marclou ·
You can't lose in entrepreneurship.
You either win, or you learn.
- Gergely Orosz
@GergelyOrosz ·
Example of the impact of "good" AI:
Speeding up processes that seemed IMPOSSIBLE to speed up in the past! So challenging timelines from pre-AI.
These will include doing away w decades-long assumptions like "it takes at least 2-3 days for Legal to review contracts over $100K"