Yup
You’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 They will be generally superseded by more capable specialized harnesses.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.
Introducing Guided Reviews: the better way to review a PR
A big diff is shown in file order, so you spend the first half hour jumping between files, working out what the PR does
Guided Reviews does that for you
- Overview shows the before vs after like a show-me. This way you understand what's changed on a high level
- Files are grouped into chapters, each explained in plain words so you review one idea at a time
- Only pay attention to what matters! The core change comes first. Database, tests and generated files come last
Plugins and guided reviews are here!
Capy 0.4.4
• Plugins from the Capy marketplace
• A guide on every reviewed PR
• Custom models on your own key
• Desktop threads without a project
• Fixes and improvements
capy.ai/changelog/0.4.4
Uncle OJ retweeted
big part of adulting is learning how to sleep with inexpressible pain in your heart
Uncle OJ retweeted
Ownership is not a feeling. It's a decision.
Most people treat their standards as a response to their environment performing when conditions are good, pulling back when they're not.
I've built my entire career on the opposite principle.
Uncle OJ retweeted
Google releases EmbeddingGemma 2, a new open model that runs locally on 0.5GB RAM.
The 740M parameter Apache 2.0 model combines a 270M text model with vision (170M) + audio (300M).
Run & train the model via Unsloth.
GGUF: huggingface.co/unsloth/embed…
Guide: unsloth.ai/docs/models/embed…
Uncle OJ retweeted
We haven't stopped growing since we launched our new ChatGPT plugin last Tuesday.
I've never seen anything like this, we added 500K in ARR this week only!
Uncle OJ retweeted
Today we shipped Memory and Dreaming in Devin: persistent self-cleaning memory for agent sessions.
The standard is OSS and also works across any harness in any environment. ⚡
Introducing Dreaming: Across sessions, Devin builds a memory graph of how you like to work
At night Devin self-improves its memory to remove stale records and discover latent information
We are creating an OSS standard called Agent Memory Repo: cognition.com/agent-memory-r…
1/ Agent cursors were never much to look at.
Today we're introducing 6 new cursor motions in Cua Driver, each hand-crafted and perfectly timed. We studied how people aim a mouse, built 82 motions in a playground, and kept the best six.
It's all open source: github.com/trycua/cua
Yo!
For decades, researchers have sought materials that sort electrons by spin while their magnetism cancels.
In 3 days, 90+ Opus 5.5 agents helped us uncover two room-temperature magnetic semiconductor candidates in simulations: YBaMnFeO₅ and KV[Cr(CN)₆].
KV[Cr(CN)₆] was synthesized back in 1999. Its predicted ability to sort electrons by spin appears to have been hiding in plain sight for 27 years.
Uncle OJ retweeted
every team building a serious agent ends up drawing this tree
sentry spent ~4 months and 100k lines on theirs. stripe, shopify, harvey, ramp, and sierra built their own
the harness isn't the hard part. everything around it is
that's the layer we're building in the open at @omnaraai
before @eve, we had built an agent called fluffles. it ran on a mac mini that sits across me.
the goal was for it to be a god agent - an agent so powerful it could operate indistinguishably from a human, with no restrictions whatsoever.
we wanted to give it a credit card, phone number, patched browser - the whole 9 yards.
we mapped out what primitives it would need, and came up with the architecture shown. we thought it would be straightforward.
but building the harness was unbelievably painful. from automations to subagents.
there wasn't one specific thing that was hard, it was that the surface area of shit that can go wrong is unbounded.
when eve came out, we ported over almost immediately. the scaffolding let us focus on agent behavior instead of the intricacies of a slack integration.
we're excited to show you our work, and will be launching this week.
Uncle OJ retweeted
Team Grok Bots are insanely powerful. You can basically create any custom tool or workflow and have your entire org able to take advantage of it in minutes. Possibilities are endless.
Uncle OJ retweeted
We are making Markdown files work natively across Google Drive and Docs.
You can now preview .md files in Drive, open them in Docs, edit them, comment on them, and collaborate without converting the file into a Google Doc!
Uncle OJ retweeted
I remember when I wrote my first memory system in 2023 for agents (not just RAG, but complete with dreaming, compaction, synthetization, etc)
We've come a very long way! If you're a context engineer, I highly recommend reading the technical explainer for this one
Introducing Dreaming: Across sessions, Devin builds a memory graph of how you like to work
At night Devin self-improves its memory to remove stale records and discover latent information
We are creating an OSS standard called Agent Memory Repo: cognition.com/agent-memory-r…
Uncle OJ retweeted
This happens to smart people because of:
1. Deep-rooted identity of “I am good at product” (vs. “I am good at winning” or something like that)
2. Moral aversion against marketing & distribution
3. A habit of seeking virtue points by proclaiming “I just want to serve my users”
