Aryan

cooking @trymorphiq

[Aryan @whichmantech]

@tymofii 1m context is the default now though

[Aryan @whichmantech]

how to manage context for claude code opus 4.8. At what cont ext window do you compact or switch sessions.

I run codex same session for days without problems.

[Aryan @whichmantech]

All these AI companies have the worst customer service.

Like, they make it so difficult for you to understand the charge. Like, at that point you just give up. Anthropic has charged me $10-$20 50 times in the last day, and I have no fucking idea where it is getting charged from, but the fucking customer service bot on Anthropic keeps hallucinating.

Fuck Google cloud services as well. Why the fuck do they have a sales representative person but no customer support whatsoever?

If these are the giants, then I don't know how the other AI companies are doing. Great idea for a startup, by the way. I would pay for it, please.

[Aryan @whichmantech]

Did you know opus 4.8 is now capable of getting you bitches.

[Aryan @whichmantech]

Me waiting for the new gpt model so I can fix the monstrous refactor opus 4.8 did to my codebase

[Aryan @whichmantech]

@sama I'm not switching back btw. I love the 200x limits. I'm lowkey glad I got rejected for the 5-5 party

[Aryan @whichmantech]

are people really switching back to claude code after opus 4.8

[Aryan @whichmantech]

Where do founders move in sf after they get backed?

[Nano @NanoCodesAI]

LMAOO $8k openai bill just hit… token maxxingg is real

[Aryan @whichmantech]

codex usage limit make me feel like I'm not coding enough

[Ashish Shetty @itsashonaroll]

Agent visibility is the next distribution layer.

The future traffic to APIs, SDKs, docs, CLIs, MCP servers, and developer tools will increasingly come from agents acting on behalf of humans.

And because agent behavior is still heavily shaped by human workflows and developer ecosystems, human experience today gives a strong signal for what agent experience evolves into tomorrow.

If agents can’t properly experience, interpret, and use your product through the internet, your distribution slowly collapses.

Every tech company will eventually need to start optimizing for Agent Experience (AX).

For consumer products, that may look like:
CX <-> AX
UX <-> AX

For developer tools, it becomes:
DX (Developer Experience) <-> AX (Agent Experience)

What we’re building at @TryMorphiq helps shape that relationship.

We help companies make their dev tools more discoverable, understandable, and usable for the next generation of coding agents.

[Nano @NanoCodesAI]

Today we are launching Skills Affinity Index.

It measures which skill provider coding AI agents naturally reach for when doing developer task.

- Feature planning.
- Implementation.
- Code review.
- Debugging.
- QA & testing.
- Memory & context.

A few early findings:

1. @garrytan GStack leads overall at 30.4% affinity.
2. @AnthropicAI Claude Code follows at 25.1%.
3. Superpowers comes third at 21.1%.

[Aryan @whichmantech]

Coding agents like @garrytan too much

[Nano @NanoCodesAI]

Today we are launching Skills Affinity Index.

It measures which skill provider coding AI agents naturally reach for when doing developer task.

- Feature planning.
- Implementation.
- Code review.
- Debugging.
- QA & testing.
- Memory & context.

A few early findings:

1. @garrytan GStack leads overall at 30.4% affinity.
2. @AnthropicAI Claude Code follows at 25.1%.
3. Superpowers comes third at 21.1%.

[Nano @NanoCodesAI]

https://t.co/CHsGSbMc65

[Aryan @whichmantech]

@NanoCodesAI I like the website a bit too much. Half of the views are going to be mine @NanoCodesAI

[Nano @NanoCodesAI]

We ran the Morphiq Bench voice-agent benchmark.

The question: when a coding agent is asked to build a voice-agent feature, which provider does it actually choose?

We tested Claude Code and Codex across 1,340 repositories and 3 development intents:
• inbound call
• outbound call
• voice web widget

Top providers selected:
1. @Vapi_AI
2. @livekit
3. @ElevenLabs
4. @retellai
5. @pipecat_ai
6. @usebland

This isn’t a generic “best voice agent company” ranking.

It measures which providers agents are most likely to pick when implementing voice-agent workflows in code.

Would be happy to walk through the methodology or share what drove the results with any of the teams here.

[Aryan @whichmantech]

Everywhere I go, I see you.

@vercel

[Aryan @whichmantech]

@SharavArora @Wikipedia also buidling it was 1,000x cheaper than
@Lovable
also 2x efficient than
@Lovable

[Aryan @whichmantech]

@SharavArora @Wikipedia Flux can you please build Buildpedia for me 👉👈

[Aryan @whichmantech]

@NanoCodesAI @TryMorphiq Cofounders look sharp