@iso_morph

agent harnesses @wearerandomlabs

discord.gg/RBDqGJqkc6
Joined November 2021
  • Tweets6.5K
  • Following993
  • Followers10.2K
148Media

Designing a programmable runtime for agent orchestration

Article · @iso_morph
19
47
6
428
871,712
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
11
1,319
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
163
I am going to be the Sam Lambert of sandbox CEOs and @freestyle_dev will be the Planetscale.
5
1
42
3,159
He’s like the Tibo of reflection ai
Jake Nations
@nayshinsOct 18
We can do resets too!
3
590
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
Jake Nations
@nayshinsOct 16
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
5,055
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
41
10
496
56,530
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
1,033
I feel that certain sandbox providers may have never tried EC2. t4g.nano costs $0.0042/hour. Worth considering a warm pool of that.
17
5
395
48,319
akira retweeted
jz
@jzlegionOct 8
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!
Catalyst
@CatalystLabsXOct 8
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.
126
21
7
488
40,875
Maybe Calvin (1992) knew it all along
35
998
60
8,334
203,436
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
66
96
394
518,608
A prediction: For the past 9 months there has been a reasonable expectation that every engineer you speak to has a $200 subscription to either OpenAI or Anthropic. That may be coming to an end with the rise in open models. Companies like baseten may offer inference passes and companies like Devin and Random Labs may become more serious contenders. This hinges on cost per task for most tasks agents complete continuing to drop at current rates.
7
1
23
2,412
As models get smarter I am more and more convinced that @a1zhang's mismanaged genius nomenclature is representative of whats going on There is no reason for these models to struggle the way they do at this point
1
2
62
6,111
inference is going to be a trillion dollar market in the next 18 months i want to power all of it yes thats delusional but thats the mindset
30
20
5
392
30,305
Still true. The models can make things work but I’m not sure what even a reasonable objective would be to get past where they are right now.
akira
@iso_morphSep 23
My understanding of software engineering has changed dramatically in the past month or so
5
33
2,827
Opus IS significantly faster than Astra xhigh for what its worth
akira
@iso_morphOct 2
back in the distributed systems bunker for a bit today Testing opus 5.5 vs Astra Its interesting. Opus 5.5 feels like an Opus model Astra is somewhat different in how it approaches its correctness. Opus seems to want to shoot for a full solution that I would like to read, whereas astra is mentioning invariants more. I need to get opus to use its math skills more
1
20
1,869
back in the distributed systems bunker for a bit today Testing opus 5.5 vs Astra Its interesting. Opus 5.5 feels like an Opus model Astra is somewhat different in how it approaches its correctness. Opus seems to want to shoot for a full solution that I would like to read, whereas astra is mentioning invariants more. I need to get opus to use its math skills more
1
1
10
2,620
The cluely architecture diagram got one thing right @Cloudflare workers just scale
1
4
1
79
24,580
Stolen tweet btw
4
1,579
Agents write application code, but you still get paged at 2am when it breaks. We wanted to know whether AI could handle that part of the job too. Introducing Incident Arena: a benchmark that puts coding agents on call! Check out our paper & full dataset release below!
54
54
19
255
58,278
Load more