alasano

"Start a new project. Every language, every tool, every hosting model available. You pick serverless."

Picking serverless as the leading example to show off perfection.

You can use this endpoint for quota reset times.

Just ask Codex to use its local auth token as a bearer token and send a GET request to it. The response includes "available_count" and "credits[].expires_at". Or script it yourself obviously.

https://chatgpt.com/backend-api/wham/rate-limit-reset-credit...

You're using Opus 4.8 and then Sonnet 5 which is both worse and more expensive in practice than Opus.

Nah that was it, now that it's fixed I'll actually take a look!

I love the flexibility of agents in a regular harness but mostly for investigation, planning etc.

Once I actually have my plan/spec, it's the same process every time, it needs to be as deterministic as possible, using agents as tools throughout the process.

Yada yada yada introduction done so I can drop the link to what I'm building which is exactly that

https://engine.build

I keep pushing back open sourcing it but it's truly close to ready and will be fully free to use.

It's the most advanced deterministic agentic orchestrator on the planet.

As a general rule I don't use new products whose websites don't resize properly on mobile.

If you fuck that up, makes me wonder what other obvious stuff you fuck up.

They get to pretend to be on the best side of every position simultaneously.

They're only encrypting thinking because AI is so dangerous and only they can be trusted to be in control of AGI.

This happens to align with lining their pockets as well.

I think for a company in AI specifically it's worse.

It makes me feel like either

1) you don't use the models enough to know how they write

2) you're not self aware enough to know it matters

3) you're oblivious to the situation overall

4) you don't respect your readers

There's no good scenario.

My global CLAUDE.md/AGENTS.md etc have strict rules to never use subagents without approval or when specifically requested except for whitelisted scenarios.

I think that's the way to go most of the time

I'm building something for that.

I've taken a bit longer than I wanted but it will be open sourced soon.

It's a durable orchestration engine that takes in specs/requirements and coordinates agents externally (meaning the engine drives the loop, not an agent) until the work is fully implemented/verified and reviewed.

It's meant to be used with any harness as basically the last step. You plan your work with whatever LLM you use and then hand off implementation to the engine (through an MCP server or other surfaces)

It can use your OpenAI/Anthropic subscriptions or any other provider and you can mix and match models across implementation and review in any way you want with fan out for parallel reviewers and more.

The goal is to produce high quality unsupervised code that matches your requirements and is reviewed throughout the implementation rather than at the end only, so that mistakes don't compound.

https://engine.build if you want to get notified when it releases.

I use zellij a lot and created myself a zellij skill for an agent to manage my sessions/layouts in zellij directly.

So for a new worktree the agent can create a tab in zellij with multiple panes, properly named etc.

It works really nicely.

Although since I got the 52 inch Dell monitor I tend to just put everything visible at all once most of the time.

A better version of Red Alert 2 is insanely high praise.

I'll add it! I like your website by the way, something satisfying about the design.

Sure thing I'll add it!

We have this page which compares a whole bunch of sandbox providers in different categories

https://engine.build/lab/agent-sandboxes

Will add MicroVMs there today (and any others that are missing if you let me know!)

OpenRouter Fusion is basically ask N models + synthesizer step.

This is ask a special orchestrator they built, which is in front of a bunch of models, which model would suit the request best.

Regular Fugu seems to be just "pick the best model and route the request there"

Fugu Ultra can generate like a little mini workflow/plan instead to achieve a result

1. Ask GPT to derive the math. 2. Ask Opus to check for implementation/security issues. 3. Ask Gemini to synthesize or resolve disagreement. 4. Return final answer.

I could be wrong but seems to be that at a glance, so I think it's more dynamic than OpenRouter Fusion.

I understand that hermes needs to do be able to do "everything" but I can't stand how much crap comes along with it.

It feels like when you do a fresh Windows install and you have to debloat it from all the spyware and candy crush type games.

Pi is the perfect clean slate, I absolutely love it.

If an AI customer service agent disclosed what capabilities it has that go beyond what I can do by myself, that would be an immediate improvement.

Gonna give this the biggest compliment and highest honor I give alternative hacker news interfaces: I don't hate it!

I really like the simplicity of HN and this kinda keeps it (somewhat) in a way that I like.

When the comment overlay is open however, I was expecting tapping outside of it to close the overlay btw, not to let me tap the underlying stories and get redirected.

That's a really fun project! What kind of issues are you facing that requires that much rework? Is it that the manufacturing of the book wasn't precise enough and the mini demos don't work perfectly?

Beyond the target age of your book but when I was 7-8 years old my favorite book was a science book that had interactive experiments. Hope your book leaves the same kind of positive and memorable impression on kids.

I'm working on https://engine.build , releasing early next week (OSS and Free)

It's a durable orchestration loop for implementing code with LLMs that forces review and verification gates until the code matches exactly what you asked for.

It's complementary to any existing harness or tools you use, you investigate and plan your work and simply have your agent hand off the implementation to the engine.

You can have Opus 4.8 implementing, GPT 5.5 and DeepSeek reviewing in different roles etc, mix and match however you like.

It also supports sandboxing out of the box, starting with the YC backed Microsandbox.

I love ntfy and use it every day, thanks for having created it!

There's an often hard to express subjective experience you get with a new model, especially if you spend a lot of time trying out different ones.

I believe the people who feel like Fable is a big improvement, for me it's just much more reasonable and grounded.

It makes me realize how much of a try hard over optimizing planner GPT 5.5 can be. I've been fighting it often to simplify plans.

But no matter the model you can't trust them to actually deliver on very long tasks while maintaining quality. At least not without external orchestration and review.

Obviously not what he meant at the time but hilarious(ly sad) in retrospect.

I'm building https://engine.build

It's meant for the implementation of well defined tasks/specs while orchestrating a review/fix/verify loop.

Every day I have implementations running for hours non stop, it's simply the time it takes to get a proper and well reviewed implementation with LLMs imo.

It's clearly not for you, you built yourself a version that works for you.

It's not me for either currently but that doesn't mean it's not useful.

Although there's a ton of other providers with their own more or less managed/opinionated flavor of agentic sandboxes.

We cataloged a bunch here

https://engine.build/lab/agent-sandboxes

I'll also add boxes.dev to that list.

But yeah overall your tone was asshole flavored lol. Maybe being a bit of a hater too.

Their initial budget for determining how much value AI adds is $18,000 per engineer.

From what I've read so far it's less about Mythos being much better at tasks in isolation.

Security wise, it's about being able to find and chain multiple vulnerabilities to actually create viable exploits.

So I would imagine that if you were using it for regular software development you may not feel that it's that different unless used in a particular way?

Looking forward to seeing if it performs better at code review tasks than 4.7 which is terrible at finding issues.

What's that from? OpenSpec docs?