IKcode | Igor Wnek
@ikcode.dev
👨🏻💻 Principal Dev | Tech Educator | AI & Copilot Advocate
Helping devs & tech leads master Copilot, Perplexity & AI for smarter, faster programming and new tech adoption
🎥 YT: IKcode Igor Wnek | 💻 github.com/IgorWnek | https://github.com/ikcode-dev
Helping devs & tech leads master Copilot, Perplexity & AI for smarter, faster programming and new tech adoption
🎥 YT: IKcode Igor Wnek | 💻 github.com/IgorWnek | https://github.com/ikcode-dev
I'm going to test it out, thanks Elio!
October 19, 2026 at 7:09 PM
I'm going to test it out, thanks Elio!
Huntley's article: https://ghuntley.com/replaced/
Show Your Work! by Austin Kleon, a short book I reread regularly: https://austinkleon.com/show-your-work/
What I share as open source: https://github.com/IgorWnek
Show Your Work! by Austin Kleon, a short book I reread regularly: https://austinkleon.com/show-your-work/
What I share as open source: https://github.com/IgorWnek
October 12, 2026 at 1:01 PM
Huntley's article: https://ghuntley.com/replaced/
Show Your Work! by Austin Kleon, a short book I reread regularly: https://austinkleon.com/show-your-work/
What I share as open source: https://github.com/IgorWnek
Show Your Work! by Austin Kleon, a short book I reread regularly: https://austinkleon.com/show-your-work/
What I share as open source: https://github.com/IgorWnek
Then show your work. Publish the repo, write a short post, share what broke.
One piece of advice: this week, build a small proof of concept you've always wanted, with a coding agent. Then publish it, together with what you learned.
One piece of advice: this week, build a small proof of concept you've always wanted, with a coding agent. Then publish it, together with what you learned.
October 12, 2026 at 1:01 PM
Then show your work. Publish the repo, write a short post, share what broke.
One piece of advice: this week, build a small proof of concept you've always wanted, with a coding agent. Then publish it, together with what you learned.
One piece of advice: this week, build a small proof of concept you've always wanted, with a coding agent. Then publish it, together with what you learned.
Pay for AI yourself and use it on your own code. If your company doesn't allow AI, keep your subscription away from its code and your clients' code.
A $20 plan is enough to start. Treat it as an investment, not a cost.
A $20 plan is enough to start. Treat it as an investment, not a cost.
October 12, 2026 at 1:01 PM
Pay for AI yourself and use it on your own code. If your company doesn't allow AI, keep your subscription away from its code and your clients' code.
A $20 plan is enough to start. Treat it as an investment, not a cost.
A $20 plan is enough to start. Treat it as an investment, not a cost.
Using AI at work isn't enough. Build the thing you've always wanted to build. With coding agents, that takes evenings, not months, and that experience is what makes you valuable at work.
October 12, 2026 at 1:00 PM
Using AI at work isn't enough. Build the thing you've always wanted to build. With coding agents, that takes evenings, not months, and that experience is what makes you valuable at work.
Doing more has consequences too: far more code to review and a very different way of working. You'll discover that along the way, and it's normal. More on that in future posts.
October 12, 2026 at 1:00 PM
Doing more has consequences too: far more code to review and a very different way of working. You'll discover that along the way, and it's normal. More on that in future posts.
I still know engineers who say they won't use AI. AI won't replace them. Engineers who use it every day will.
Without AI, the work is too slow compared to theirs. They try more ideas, ship more, and still have time to check what they ship.
Without AI, the work is too slow compared to theirs. They try more ideas, ship more, and still have time to check what they ship.
October 12, 2026 at 1:00 PM
I still know engineers who say they won't use AI. AI won't replace them. Engineers who use it every day will.
Without AI, the work is too slow compared to theirs. They try more ideas, ship more, and still have time to check what they ship.
Without AI, the work is too slow compared to theirs. They try more ideas, ship more, and still have time to check what they ship.
"If your team is too busy doing their 'normal job' to experiment with AI, you're preparing them to be replaced."
Geoffrey Huntley wrote that last week. I agree, and I'd go further.
Geoffrey Huntley wrote that last week. I agree, and I'd go further.
October 12, 2026 at 1:00 PM
"If your team is too busy doing their 'normal job' to experiment with AI, you're preparing them to be replaced."
Geoffrey Huntley wrote that last week. I agree, and I'd go further.
Geoffrey Huntley wrote that last week. I agree, and I'd go further.
GPT-6 Luna costs the same for shorter prompts. Anthropic's table puts Haiku 5.5 ahead, 39.2% vs 16.4% on Terminal-Bench 4.0.
My guess: GPT-6.1 Luna lands tomorrow. GPT-6.1 Sol came the day after Sonnet 5.5.
https://www.anthropic.com/claude-haiku-5-5
My guess: GPT-6.1 Luna lands tomorrow. GPT-6.1 Sol came the day after Sonnet 5.5.
https://www.anthropic.com/claude-haiku-5-5
October 7, 2026 at 9:11 PM
GPT-6 Luna costs the same for shorter prompts. Anthropic's table puts Haiku 5.5 ahead, 39.2% vs 16.4% on Terminal-Bench 4.0.
My guess: GPT-6.1 Luna lands tomorrow. GPT-6.1 Sol came the day after Sonnet 5.5.
https://www.anthropic.com/claude-haiku-5-5
My guess: GPT-6.1 Luna lands tomorrow. GPT-6.1 Sol came the day after Sonnet 5.5.
https://www.anthropic.com/claude-haiku-5-5
Same update: Sonnet 5.5 cache reads drop from $0.20 to $0.10 per million tokens. Anthropic puts the saving at around 20% on most agentic work, in line with my own estimate.
With Haiku taking the right subagent work, I expect my Claude Max plans to go much further.
With Haiku taking the right subagent work, I expect my Claude Max plans to go much further.
October 7, 2026 at 9:11 PM
Same update: Sonnet 5.5 cache reads drop from $0.20 to $0.10 per million tokens. Anthropic puts the saving at around 20% on most agentic work, in line with my own estimate.
With Haiku taking the right subagent work, I expect my Claude Max plans to go much further.
With Haiku taking the right subagent work, I expect my Claude Max plans to go much further.
I expect it to earn a place as a subagent on well-specified work: implementing a plan, triage in code review, codebase research. Sonnet and Opus keep complex agentic coding.
Prompting guide tip: at low and medium effort it sometimes reports a change as done without running a check. Name the check.
Prompting guide tip: at low and medium effort it sometimes reports a change as done without running a check. Name the check.
October 7, 2026 at 9:11 PM
I expect it to earn a place as a subagent on well-specified work: implementing a plan, triage in code review, codebase research. Sonnet and Opus keep complex agentic coding.
Prompting guide tip: at low and medium effort it sometimes reports a change as done without running a check. Name the check.
Prompting guide tip: at low and medium effort it sometimes reports a change as done without running a check. Name the check.
Claude Haiku 5.5 is out, almost a year after Haiku 4.5. On paper, it was worth the wait.
Per million tokens, for prompts up to 100K:
Input: $0.10 (Haiku 4.5: $1)
Output: $0.50 (Haiku 4.5: $5)
Longer prompts cost half as much as on Haiku 4.5. Anthropic puts the average saving at around 75%.
Per million tokens, for prompts up to 100K:
Input: $0.10 (Haiku 4.5: $1)
Output: $0.50 (Haiku 4.5: $5)
Longer prompts cost half as much as on Haiku 4.5. Anthropic puts the average saving at around 75%.
October 7, 2026 at 9:11 PM
Claude Haiku 5.5 is out, almost a year after Haiku 4.5. On paper, it was worth the wait.
Per million tokens, for prompts up to 100K:
Input: $0.10 (Haiku 4.5: $1)
Output: $0.50 (Haiku 4.5: $5)
Longer prompts cost half as much as on Haiku 4.5. Anthropic puts the average saving at around 75%.
Per million tokens, for prompts up to 100K:
Input: $0.10 (Haiku 4.5: $1)
Output: $0.50 (Haiku 4.5: $5)
Longer prompts cost half as much as on Haiku 4.5. Anthropic puts the average saving at around 75%.
I leave room for another provider or tool to earn a role. Argon leads the broader Vals Index; task mix matters. I'd compare accepted results, review time, failures, and cost on my own work.
Terminal comparison:
https://www.vals.ai/benchmarks/terminal-bench-4
Terminal comparison:
https://www.vals.ai/benchmarks/terminal-bench-4
October 5, 2026 at 3:45 PM
I leave room for another provider or tool to earn a role. Argon leads the broader Vals Index; task mix matters. I'd compare accepted results, review time, failures, and cost on my own work.
Terminal comparison:
https://www.vals.ai/benchmarks/terminal-bench-4
Terminal comparison:
https://www.vals.ai/benchmarks/terminal-bench-4
Vals' Mini-SWE-agent terminal runs put Argon behind Opus, Sonnet, and Astra. It scores above Sol 6.1, but costs about 10x as much per test at the published API rates. Some Claude tasks used fallbacks.
That doesn't establish value under my subscriptions.
That doesn't establish value under my subscriptions.
October 5, 2026 at 3:45 PM
Vals' Mini-SWE-agent terminal runs put Argon behind Opus, Sonnet, and Astra. It scores above Sol 6.1, but costs about 10x as much per test at the published API rates. Some Claude tasks used fallbacks.
That doesn't establish value under my subscriptions.
That doesn't establish value under my subscriptions.
Could Gemini 4 Argon replace Opus 5.5, Sonnet 5.5, GPT-6 Astra, or GPT-6.1 Sol?
Access is still restricted. Argon leads Google's DeepSWE comparison, but trails Opus and Astra on FrontierSWE. I'd evaluate specific tasks before changing a default.
Access is still restricted. Argon leads Google's DeepSWE comparison, but trails Opus and Astra on FrontierSWE. I'd evaluate specific tasks before changing a default.
October 5, 2026 at 3:45 PM
Could Gemini 4 Argon replace Opus 5.5, Sonnet 5.5, GPT-6 Astra, or GPT-6.1 Sol?
Access is still restricted. Argon leads Google's DeepSWE comparison, but trails Opus and Astra on FrontierSWE. I'd evaluate specific tasks before changing a default.
Access is still restricted. Argon leads Google's DeepSWE comparison, but trails Opus and Astra on FrontierSWE. I'd evaluate specific tasks before changing a default.
I started new initiative where I'm going to share lot's of stuff around agentic product engineering. I start with my symlinks-free dotfiles - github.com/theultimate-...
My setup is based on #herdr with few other #terminal based apps. I'm going to add there more soon.
Let me know what's your setup!
My setup is based on #herdr with few other #terminal based apps. I'm going to add there more soon.
Let me know what's your setup!
GitHub - theultimate-dev/dotfiles: The Ultimate Dev's official dotfiles: a terminal-first macOS stack for agentic product engineers. The installer, the core tools and every config, with the reasoning ...
The Ultimate Dev's official dotfiles: a terminal-first macOS stack for agentic product engineers. The installer, the core tools and every config, with the reasoning written down and shared with...
github.com
September 13, 2026 at 5:53 PM
I started new initiative where I'm going to share lot's of stuff around agentic product engineering. I start with my symlinks-free dotfiles - github.com/theultimate-...
My setup is based on #herdr with few other #terminal based apps. I'm going to add there more soon.
Let me know what's your setup!
My setup is based on #herdr with few other #terminal based apps. I'm going to add there more soon.
Let me know what's your setup!
And that's a clever solution. 👍
September 12, 2026 at 9:10 AM
And that's a clever solution. 👍
If nice UI and ability to use Claude Code, Codex and Grok Build in the same tool is what you expect, then t3.codes is the tool you should test out.
I've been using it for few days and I'm impressed.
It's alpha version, but very usable. 🔥
I've been using it for few days and I'm impressed.
It's alpha version, but very usable. 🔥
T3 Code
T3 Code — The open-source control plane for coding agents.
t3.codes
August 23, 2026 at 1:54 PM
If nice UI and ability to use Claude Code, Codex and Grok Build in the same tool is what you expect, then t3.codes is the tool you should test out.
I've been using it for few days and I'm impressed.
It's alpha version, but very usable. 🔥
I've been using it for few days and I'm impressed.
It's alpha version, but very usable. 🔥
3/3 The proactive move is counterintuitive: shrink the Concern circle, expand the Influence one. AI engineer: stop chasing releases, ship the eval. Product engineer: stop reading the roadmap, talk to five users. Principal: pick the two places where you actually move the system. Sick! 💪🏻
May 20, 2026 at 9:03 PM
3/3 The proactive move is counterintuitive: shrink the Concern circle, expand the Influence one. AI engineer: stop chasing releases, ship the eval. Product engineer: stop reading the roadmap, talk to five users. Principal: pick the two places where you actually move the system. Sick! 💪🏻
Covey's distinction: Circle of Concern (everything you care about) vs Circle of Influence (what you can actually affect). Most engineers I know - drown in the Concern circle. Model news, org politics, every team's stack choices.
May 20, 2026 at 8:36 PM
Covey's distinction: Circle of Concern (everything you care about) vs Circle of Influence (what you can actually affect). Most engineers I know - drown in the Concern circle. Model news, org politics, every team's stack choices.
Re-reading "The 7 Habits of Highly Effective People". The 1st Habit - "Be Proactive" - reads differently when you're a product engineer, an AI engineer, or principal-ish on your team. It's not "take initiative". It's about where you choose to spend your attention.
May 20, 2026 at 8:33 PM
Re-reading "The 7 Habits of Highly Effective People". The 1st Habit - "Be Proactive" - reads differently when you're a product engineer, an AI engineer, or principal-ish on your team. It's not "take initiative". It's about where you choose to spend your attention.
Finally, after few years I've updated my profile photo 😅
March 7, 2026 at 10:40 AM
Finally, after few years I've updated my profile photo 😅
Reposted by IKcode | Igor Wnek
“Go 1.26 is released” by Carlos Amedee, on behalf of the Go team — https://go.dev/blog/go1.26
#golang
#golang
February 10, 2026 at 8:31 PM
“Go 1.26 is released” by Carlos Amedee, on behalf of the Go team — https://go.dev/blog/go1.26
#golang
#golang
Awesome news! Thanks! 🚀
February 10, 2026 at 8:44 PM
Awesome news! Thanks! 🚀