akira (@iso_morph) header
akira (@iso_morph) profile picture

agent harnesses @wearerandomlabs

Joined November 2021
Photo by akira (@iso_morph)Photo by akira (@iso_morph)Photo by akira (@iso_morph)Photo by akira (@iso_morph)Photo by akira (@iso_morph)
What the
Some news: I’m joining OpenAI to lead product management for Core Products! I have a lot of respect for OpenAI for showing the world that scaling works, for bringing AI to over a billion people, and for believing great products are core to the mission. I’m excited to work with @thsottiaux, an incredible PM team, and everyone across OpenAI. Together, we’ll build agents that have your back and your team’s, and keep you in control, so you get more time for the people and work you love. Lots to learn, and lots to build. Please keep your feedback coming!
1
4
517
Nov 4 is acquisition day apparently: > Pierre > HumanLayer > Conductor Who else got acquired today??
3
8
829
Not only am I back to agents, slate is getting a massive overhaul What do you wish your agents could do on their own? And what have you hacked together for them? Lots of people talking about their software factories And how much of that swarm scaling is coordination overhead?
I'm finally working on actual agent engineering again. A few observations: Seems like everyone has finally caught onto the idea of sliding window compaction. ...
5
18
1,140
Also, the labs are telling you this but you don't need 1000 subagents for a task that only demands 2. Maybe worth exploring scaling agent count and figuring out where the compute gets spent
Replying to @iso_morph
Subagent efficiency is important now that labs are prioritizing fan out.
1
11
1,086
I'm finally working on actual agent engineering again. A few observations: Seems like everyone has finally caught onto the idea of sliding window compaction. ...
4
2
1
239
38,143
Memory seems like it still isn't solved? Whats the best implementation out there?
8
1
25
5,705
IMO there might be a higher upper bound on what open source models can do that we havent tapped into
1
11
5,063
Been messing with Opus 5.5 and boy does this model love to overcomplicate the abstractions it is implementing. So many things can just be written inline very simply What's interesting is it is reasoning more clearly and directly about patterns it uses Pretty good model
3
13
1,448
The code it writes looks less minified than astra though so thats a plus Astra is much more precise in how it solves problems from what I can tell
1
246
I am going to be the Sam Lambert of sandbox CEOs and @freestyle_dev will be the Planetscale.
5
1
42
3,199
He’s like the Tibo of reflection ai
We can do resets too!
3
658
Another casualty to sleep deprivation is that I forgot to add the final thanks to this thread... This is the result of a tons of work from a great team besides myself: @GerardMTFB @akseljoonas @depthfirstsearc @chetantekur And if you could not tell already the architecture of this harness is inspired by @pidotdev by the goat himself @badlogicgames and OpenAI Codex
Ok can finally talk about what I’ve been working on at Reflection. Introducing Mirror, our own open source coding agent optimized for Beam. I started the mirror project when I first joined Reflection, and it has gone through many iterations since then. Install it today with: uv tool install reflection-mirror github.com/reflection-oss/mi…
3
3
1
39
5,119
Ok can finally talk about what I’ve been working on at Reflection. Introducing Mirror, our own open source coding agent optimized for Beam. I started the mirror project when I first joined Reflection, and it has gone through many iterations since then. Install it today with: uv tool install reflection-mirror github.com/reflection-oss/mi…
44
40
10
496
57,778
An agent can do all the non-structural parts of systems eng as far as I can tell This is actually good because you can design systems and think through them and then magically they exist
3
12
1,091
I feel that certain sandbox providers may have never tried EC2. t4g.nano costs $0.0042/hour. Worth considering a warm pool of that.
15
5
394
48,383
akira retweeted
extremely excited to announce our $30m raise for Catalyst. we are looking for incredible engineers to explore the future of finance as we enter the dawn of superintelligence please reach out if this is you!
Introducing Catalyst. What do you believe? How would you trade on it? You notice data centers are popping-up everywhere, gold will skyrocket, or just know that Labubus will go out of fashion. Catalyst researches your ideas, builds the optimal strategy, monitors events, and executes trades. Autonomously.
130
21
7
496
41,587
Maybe Calvin (1992) knew it all along
35
993
60
8,301
204,104
Everyone in AI is building for everyone else in AI. We're building for your group chat. Introducing Charming ✨ Personal apps for us normies. Make an app for your book club, a meal planner for your family, go wild (it's free!) Build in Claude/ChatGPT, share like a Google Doc
132
65
97
396
522,978