Mir

4.4K posts

Mir banner
Mir

Mir

@mir_ow

Trying to be useful in interesting times.

World Katılım Kasım 2011
583 Takip Edilen357 Takipçiler
Mir
Mir@mir_ow·
@wesbos That’s the next Claude tool you are talking about. Another one will bite the dust 😂
English
0
0
0
1.8K
Mir
Mir@mir_ow·
Google AI Pro gives you 1,000 monthly AI credits, but Antigravity does not automatically use them once you hit model quota. You have to manually go to Agent Manager → Settings → Models → Enable AI credit overages. I have been subscribed for 3 months and only just discovered this. The credits do not roll over either. This is an incredibly confusing UX for something users are literally paying for. google support article explaining this: support.google.com/googleone/answ…
Mir tweet mediaMir tweet media
Google Antigravity@antigravity

As we balance giving the best possible quotas and maintaining fairness between users, especially under incredible demand, we will be establishing generous weekly limits for all models. This will only affect a minority of Google AI Pro users. These limits do not apply to Google AI Ultra, which continues to be the best plan for power developers!

English
1
0
0
315
ℏεsam
ℏεsam@Hesamation·
bro created an AI job search system for Claude Code that scored 700+ job applications and actually got him a job. AND IT'S NOW OPEN-SOURCE. It scans multiple company career pages, rewrites your CV per job, and even fills application forms. The repo has: > 14 skill modes (evaluate, scan, PDF, ...) > Go terminal dashboard > ATS-optimized PDF generation via Playwright > 45+ companies pre-configured (Anthropic, OpenAI, ElevenLabs, Stripe...) GitHub: github.com/santifer/caree…
English
387
2.3K
28.1K
5.7M
Mir
Mir@mir_ow·
@saiafonua @Hesamation I am not complaining it’s an honest review, As far as me working on this goes. Not interested. I have a cute little setup with playwright MCP and some custom tooling That does the thing. We should remember always less is more :)
English
1
0
31
1.1K
Mir
Mir@mir_ow·
@Marshalll_D @Hesamation I would say Playwright MCP + a chrome extension could be a good option. (chrome extension because branded browser like chrome tend to get blocked a lot less)
English
2
0
5
1.1K
Mir
Mir@mir_ow·
This makes sense, I am wondering thought what kind of tasks are you running ? You definitely have no browser access, Maybe Using brave serp api for searches but what else? I wasn’t able to find much value hosting this on VPS. As rightly mentioned by few in this thread AWS IP would be flagged by almost all website these days (specially with cloudflare managing the DNS). I am curious still on what tasks you are running on openclaw. One more thing I can add is, while using SSH may not be your preference atleast setup tailscale to easily access your control UI locally in a private manner.
English
0
0
0
1.6K
Tobias Schmidt
Tobias Schmidt@tpschmidt_·
I stopped running OpenClaw locally and moved it to a $5 Lightsail instance on AWS. Works surprisinlgy well. No need to run anything at home and/or buy a Mac mini. Problems solved: • The instance never sleeps. The agent just runs.
English
52
54
1.5K
282.9K
Mir
Mir@mir_ow·
Since Llama 4’s big release in April 2025 and nothing major since, I’ve been seriously wondering what @metaai has in the works 👀🥑
English
0
0
0
75
Mir
Mir@mir_ow·
Absolutely!! With AI agents handling more "code writing", software engineering fundamentals have never been more important, especially for freshers / new grads. Please don't go all-in on AI tools without understanding the core principles. Understanding the ins, outs, and quirks of SWE is what will set the "new" programmers apart 🙌
Gergely Orosz@GergelyOrosz

One trend that will likely return in tech, thanks to AI: Increasingly only possible to be hired as a new grad with a CS or similar degree. AI agents render writing code less relevant: but eveything else about building software (aka software engineering fundamentals) more!

English
0
0
0
154
Mir
Mir@mir_ow·
Codex is honestly really good ROI vs Claude right now. Usage is smoother than I expected, the output quality is solid, and when you crank it up to Extra High reasoning + Max models, it actually holds up, especially for multi-step refactors and “keep going until it works” tasks.
English
0
0
0
76
Mir
Mir@mir_ow·
@kirbyman01 The speed at which people are trying every new AI app is wild. But once the hype fades, consistency will be the real moat — not novelty.
English
0
0
0
24
Bryan Kim
Bryan Kim@kirbyman01·
$2M ARR in three months used to be impressive. Now we expect it within ten days. Right now, momentum is the only moat.
English
147
14
228
1.2M
Mir
Mir@mir_ow·
Back on X after a long haul, been neck-deep in AI powered coding workflows, rapid prototyping, and recreating cool ideas I spot online in record time. Can’t wait to share the experiments #BuildInPublic #AI
English
1
0
1
124
Mir
Mir@mir_ow·
@MostafaNamian @alexandr_wang @Meta @natfriedman @grok Unpopular take: Apple’s decline stories were overplayed but OpenAI might not be so lucky. When the best minds start joining your competitors instead of building with you, the tilt becomes a landslide. Feels like a watershed moment. Hard to recover when top-tier talent walks.
English
0
0
0
232
Alexandr Wang
Alexandr Wang@alexandr_wang·
I’m excited to be the Chief AI Officer of @Meta, working alongside @natfriedman, and thrilled to be accompanied by an incredible group of people joining on the same day. Towards superintelligence 🚀
Alexandr Wang tweet media
English
1.2K
1.7K
22.5K
3.8M
Mir
Mir@mir_ow·
@haider1 How are "top engineers" at meta coping up with this statement from Mark Zuckerberg ?
English
0
0
0
79
Haider.
Haider.@haider1·
Meta CEO, Mark Zuckerberg: "within 12-18 months, most of the code is written by AI" It won’t just be autocomplete. AI agents will set goals, run tests, find problems, and write better code than top engineers.
English
917
1.2K
10.7K
3.6M
Mir
Mir@mir_ow·
This cost is based on OpenAI’s retail pricing of ~$0.06/1K tokens. Internal rates may differ. Original article that covers benchmark in detail : arcprize.org/blog/oai-o3-pu…
English
0
0
0
74
Mir
Mir@mir_ow·
87.5% on ARC-AGI is impressive, but OpenAI’s o3 model ran up a $336,000 tab processing 5.6B tokens for 100 tasks. The future of AI? Bright and insanely expensive.. #AI #OpenAI #AGI
Mir tweet media
English
1
0
0
170