ai native builder / engineer at https://xitter.cf/t.co/cSbkWK7jJr lattice https://xitter.cf/t.co/bkripblBLz
Joined February 2009
- Tweets19.4K
- Following2.6K
- Followers544
- Likes29.3K
imo the bottleneck isn’t verification, it’s the accumulation of subtle deviations from your intent
this happens with about 6 agents, so with 300+ it’s going to be extreme
unless either you don’t care, or your intent is very broad and so it doesn’t matter
neither i think will result in good outcomes
It is becoming f*cking dangerous
A 23-year-old dev from China just ran 300 Claude Code agents in parallel and hooked them to a verification layer so none of them could bullshit him
He opens the live dashboard:
- 300 agents writing and checking at the same time
- Every output verified against the source in ~100 ms
- Three passes over 100 company profiles → zero errors left
- Everything dumped straight into an Obsidian vault
The trick is the split: one model does the work, a cheaper one decides if the claim is actually true. The loop doesn’t stop until everything checks out
An analyst team would bill weeks for this. He got it in one run
Same kind of Second Brain + swarm setup that keeps circulating. Bookmark the full breakdown
instead of playing games i’m getting ai agents to mod my games to make them better first
but then i never actually play i just keep doing that
Jason Liggi retweeted
Purely as a practical heuristic, I suspect a lot of people would get more out of LLMs if they switched their mental model from “software program” to “weird little guys inside my computer”.
activity indicators in lattice
the blue pulsing is working -> more agents at once, more intensity
the blue "core" is waiting
grey is idle
yellow is "needs you"
Jason Liggi retweeted
Our clinical trial participants have now used their Neuralink implants for over 50,000 hours, building one of the largest datasets of intracortical neural activity ever.
We used it to pretrain a foundation model for BCI: self-supervised neural encoders that turn noisy, drifting spikes into stable representations.
Some initial results:
• Decoders that keep working for weeks instead of days. For some users, calibration dropped from 10 min/day to 10 min/week
• Teleporting cursors that jump straight to the intended target
• A new cursor-control record of 11.32 bits per second (exceeding the performance of most able-bodied people)
We’re just getting started. Future directions include pooling data across participants, one-shot (or zero-shot) calibration, and an API for the motor cortex.
Read more:
neuralink.com/updates/pretra…
oh boy
Introducing Griffin, the first model to pass the video Turing test.
48% of people who talked to it live thought it was a real human. Previous systems have had a pass rate <3%. It is #1 on NVIDIA's benchmark for full-duplex AI video.
It’s the first Human Interaction Model (HIM).
Readers added context they thought people might want to know
The 48% figure and "video Turing test" claim are from Tavus's own study of 54 one-minute calls, not independently verified or using a standard protocol. Griffin-Lite leads NVIDIA's VideoFDB benchmark on their public leaderboard.
cellcog.ai/blog/tavus-gri…
research.nvidia.com/labs/amri/proj…
tech-ish.com/2026/10/02/tav…
Jason Liggi retweeted
🤖 Made with AI
I honestly don’t care at all that I spend 30 years of my life learning syntax and now that knowledge is essentially useless.
Frankly, I’m relieved that I don’t need to care about it anymore. That stuff never really mattered anyways. Code was always just a means to an end.
All I care about is building products that users love. Now I can do that faster. That means I can have bigger impact.
If anything, software engineers should all be celebrating. I don’t understand why you’d “mourn” not needing to write code. The code was never the point.
Jason Liggi retweeted
JUST IN: Mark Zuckerberg declares everyone will have a personal AI agent that “intimately understands you” within 5 years.
either AI hits a plateau soon, and 2040 ends up being really weird
OR it doesn't - and 2040 ends up being REALLY weird
i’ve got dynamic toast events working in crusader kings 3. an agent runs in the background, reads game state, and makes mini-events based on your personality and the personality of the characters around you
