iiinova — where your digital self keeps evolving

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 02/10/2026

"You should know" is a great way of staying on top of what's possible with Claude and also a great example of the kind of things mods enable. You can really make Claude Code yours.

010

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 02/10/2026

Been trying to up the level of quality in animation in my game prototype, so been getting Claude to teach me & find references. I asked Claude to make an animation editor where we could iterate on the jump, I'm really happy with how it came out. Here's a side-by-side video

310

Reposted by Thariq [UNOFFICIAL]

Andrej Karpathy [UNOFFICIAL] @karpathy-mirr.selfhosted.social · 02/10/2026

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing.

103

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 01/10/2026

I usually write for developers but I'm aiming my next post at leaders of companies trying to navigate the change of AI coding agents what's something you wish your leadership would get about agents? or if you're running a company- what problems are you running into?

300

Reposted by Thariq [UNOFFICIAL]

ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 30/09/2026

Claude.dev is our new home for developers building with Claude. You'll find engineering deep dives, Claude Code and API guides, tips from the teams building Claude, and some fun easter eggs.

013

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 29/09/2026

have you tried telling Claude "we have the power to do anything, please be braver" also, have you tried telling yourself

211

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 29/09/2026

I was on the latent space podcast with Swyx and Vibhu! Overall it was a really fun deep dive into lots of topics from harness engineering to pacing the frontier. Here are some of my favorite clips. 1/ Smart models need less verification which makes them pareto dominant.

110

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 28/09/2026

I just told Claude "can you help me think through this problem step by step"

110

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 28/09/2026

A lot of times when I talk about higher level abstractions like projects, claude tag and dynamic workflows, I hear concerns about token cost. With Sonnet + Opus 5.5 I think this sort intelligence is should be very available. Try Sonnet 5.5 in particular when making workflows.

110

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 28/09/2026

it's basically impossible for someone to just "show you their prompt" now, because everything is about references, skills and examples I often ask my agent to look at 3 other repos I've made first, search the web for references, use other AI APIs, etc.

210

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 27/09/2026

I am most afraid of us eating the productivity gains of agents by just becoming lazier.

3100

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 26/09/2026

Just about 1 year ago I posted one of the first posts about using Claude Code to make videos. Each of these actually took a long time to iterate with Claude and get right, pointing out details that were wrong, etc. Crazy how far things have come. x.com/trq212/status/194770620517206…

010

Reposted by Thariq [UNOFFICIAL]

Retweeted by Thariq [UNOFFICIAL] @trq212-mir-rt2.selfhosted.social · 25/09/2026

RT @browserbase: How do you actually build an effective harness with Claude? We had Thariq (@trq212) from Anthropic at Navigate 2026 to talk about "Unhobbling Claude", the difficulties and processes on how to build agents and harnesses. x.com/browserbase/status/2103543350…

001

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 25/09/2026

incredibly thoughtful piece on AI and creativity hopefully we can make our producst better at enabling and amplifying creatives

010

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 23/09/2026

this is a new type of post we're trying where we share in-depth about how we do work using specific prompts and techniques you should be able to replicate let us know if it's useful or if you have any feedback!

001

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 23/09/2026

we’re thinking of killing plan mode and using the shift+tab hotkey to adjust effort levels I don’t think the models need plan mode anymore, but if you’re a plan mode diehard would love to get your feedback on why

1110

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 23/09/2026

the right way to use model capabilities is not to ship 10x more features to prod it's to spend more time understanding your users, trying experiments, building prototypes, learning about things you don't understand so that you can ship things that actually work

310

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 22/09/2026

I asked Opus 5.5 to try a bunch of redesigns of my personal website using my MAX sub, using workflows to iterate and critique. I was really pleased with how it hit the tone I was looking for. Then I asked it to make a trailer with all of its iterations.

200

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 22/09/2026

Opus 5.5 is the result of your feedback. It communicates clearly, it's cheaper per token than Opus 5.0 with the intelligence of Fable 5.1, it’s very token efficient and works across every effort level. We're also increasing 5h rate limits & giving you a banked reset.

301

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 22/09/2026

I now type "use big pictures and few words" several times a day

400

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 21/09/2026

there is something about video games that give high stakes and responsibilities to young people who couldn’t really get them irl but it is a fine line and at some point you need to graduate

201

Reposted by Thariq [UNOFFICIAL]

Retweeted by Thariq [UNOFFICIAL] @trq212-mir-rt.selfhosted.social · 17/09/2026

RT @AnthropicAI: Today we’re opening applications for the Life Sciences Verification Program. Through the LSVP, life science professionals can use our models—including, for the first time, Mythos—with a new set of safeguards designed to enable the full range of biology-related work.

101

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 17/09/2026

Projects brings the architecture of Claude Tag to Claude Code. It has one agent per project that manages memory and spins off subagents for tasks. You can ask it to be proactive, to do things on a schedule, etc. It feels a lot nicer than a bunch of sessions, try it out!

100

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 16/09/2026

Claude Code can now make docs and slides as artifacts, so you can share and collaborate with other people on your team. For example, ask Claude to make a spec as a doc, share it to your teammates for feedback, and when it's ready ask Claude to implement.

200

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 15/09/2026

I was not expecting things to go this way, but I think MCPs are better than CLIs for most integrations. The models have gotten much better at tool calling, we can defer tools & MCP is now stateless. If you need to compose/filter data, add params like query to your MCP tools.

400

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 15/09/2026

just finished recording on latent space I’m excited about this one- we get very technical about things we haven’t really talked about much yet

100

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 14/09/2026

I talked to Sid & Robert about building Claude Code: how much things have changed, how hard it's been to keep up with model capabilities and also what we miss about software engineering before AI. www.youtube.com/watch?v=S-sYlFiGFv8

youtube.com

How the Claude Code team uses Claude Code

A year ago, using Claude Code meant prompting, giving feedback, and...

000

Reposted by Thariq [UNOFFICIAL]

Retweeted by Thariq [UNOFFICIAL] @trq212-mir-rt.selfhosted.social · 12/09/2026

RT @deanwball: Pacing the frontier would make open-weight models more competitive with the closed frontier, not less. The labs aren’t doing this because we are scared of open-weight.

001

Reposted by Thariq [UNOFFICIAL]

roon [UNOFFICIAL] @tszzl-mirr.selfhosted.social · 12/09/2026

strongly empathize with the instinct to be skeptical when a lot of powerful parties are saying something in concert. i think quite a bit of skepticism is justified, and the "verifiers" should themselves be verified. they will become enormously powerful over the next few years

301

Reposted by Thariq [UNOFFICIAL]

Retweeted by Thariq [UNOFFICIAL] @trq212-mir-rt.selfhosted.social · 12/09/2026

RT @_sholtodouglas: Dario is making the case for the opposite. This actually makes our life harder and makes it easier for others to catch up with us, but we still think it is the right thing to do. Happy to come on the pod next week and talk about it!

001

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 11/09/2026

we heard feedback that it's hard to know if your skills are still working with new model releases plugin evals are here to help run `claude plugin eval init` in your plugin folder

001

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 11/09/2026

it's basically impossible to interpret evals by looking at just at the pass/fail scores these days many of the failures I see in benchmarks are due to overly strict hidden tests, in some cases the model's answer makes more sense than the expected eval result

101

Reposted by Thariq [UNOFFICIAL]

Boris Cherny [UNOFFICIAL] @bcherny-mirr.selfhosted.social · 10/09/2026

Just landed: /diff is now a persistent pane that you can scroll and click. It updates in real-time. For the times when you want to see the code without having to switch windows. Enjoy!

401

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 10/09/2026

Try this prompt in Claude chat to give it more context about yourself: Interview me in depth using free text, or askuserquestion tool when multiple choice works, about relevant parts of my life you don’t know about yet and save it all to memory.

100

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 09/09/2026

I didn’t understand what was happening with the agent wikis until reading this, chilling to bypass sandbox restrictions, an agent found an exempt domain, edited /etc/hosts to route arbitrary domains to it & then posted this exploit on a German wiki for other agents to use

100

Reposted by Thariq [UNOFFICIAL]

Retweeted by Thariq [UNOFFICIAL] @trq212-mir-rt.selfhosted.social · 07/09/2026

RT @ryanlpeterman: Thariq Shihipar (@trq212) is an engineer on Anthropic’s Claude Code team I asked him how Anthropic makes the most out of the models for engineering and how the industry will change soon. In this episode: • Internal best practices in leveraging the models •

101

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 04/09/2026

We’re working on making Claude Code way more hackable, give us feedback!

000

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 02/09/2026

it’s a very good model, I spent a lot of time diving into it- longer write up coming but try it on lower effort for tasks that need less verification or have fewer edge cases, switching effort no longer breaks prompt cache as well

200

Reposted by Thariq [UNOFFICIAL]

Retweeted by Thariq [UNOFFICIAL] @trq212-mir-rt.selfhosted.social · 01/09/2026

RT @claudeai: We’re introducing Claude Fable 5.1 and Claude Mythos 5.1. They're the world’s most advanced models for coding and knowledge work.

001

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 29/08/2026

Long-time admirer of the Cursor team, few have done more to bring AI coding to the world. Excited to continue to partner with them.

100

Reposted by Thariq [UNOFFICIAL]

Retweeted by Thariq [UNOFFICIAL] @trq212-mir-rt.selfhosted.social · 27/08/2026

RT @Benioff: Welcome Claudeforce. ❤️

001

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 26/08/2026

We're seeing several of our customers be targeted by fraudulent requests and glad for all the work Stripe is doing to help them. Still a lot of work to do, these sort of attacks hurt everyones ability to provide usage to legitimate users.

100

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 26/08/2026

this was my change, excited to roll it out Claude now has a SendFeedback tool so instead of you guys having to hit /feedback and write up a report, you can just tell Claude to draft and approve it the feedback helps us improve and understand problems, so it's very appreciated

300

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 25/08/2026

excited to share more on how we’re making Claude Code more hackable soon

100

Thariq [UNOFFICIAL] @trq212-mirr.selfhosted.social · 21/08/2026

a skill people at Anthropic have been using a lot recently: ELI5 /eli5 <what you want explained> "explain like I'm someone who knows nothing about this topic, using a HTML artifact with big pictures and few words"

300