@gethackteam

Agents, MCP & Developer Experience at IBM ⚡ 🥑 Tech Author, Speaker, Entrepreneur 🚀 Sharing opinions (✉️ [email protected])

 Santa Clara, CA
youtube.com/@gethackteam?sub_confirmation=1
Joined November 2016
  • Tweets16.2K
  • Following2.1K
  • Followers14.2K
1.7KMedia
🍾 SOFTWARE DEVELOPER OF THE YEAR I’ve won a @hackernoon Noonies Award for my contributions to the developer community Thanks everyone for voting 🙌 🙌 – at Amsterdam, The Netherlands
13
7
4
144
marketing slop and email slop are the worst kinds of slop
19
ai turned me into a polyglot developer just this month i committed code in typescript, python, go and mainly rust
1
2
307
this will be apple’s biggest fumble ever just to give the new ceo something new to show off instead of the XXth version of the iphone
Tim Pan@mediastorm_enOct 21
iPhone Duo Review: 10,000 Folds Later...
2
663
when the junior and senior dev start vibe coding together
1
2
357
compression should be part of your harness
1
1
1
271
read my blog hackteam.io/blog/why-compres…

Why compression should be part of your agent harness | Roy Derks — Hackteam

How you can use deterministic filtering, grouping, and formatting to reduce agent context, then use semantic compression and prompt rewrites separately. Practical examples from RTK, Caveman, and...

hackteam.io
1
1
22
skill issue zsh: command not found: fm
Alex Choi
@AlexChhkOct 21
wtf i just discovered that a macbook comes with a free local LLM in your terminal
289
overengineering was the easiest way to fail your startup glad it no longer exists today
Kushal Byatnal
@kushalbyatnalOct 20
it’s hard to explain the 2010s microservices fever dream to anyone who wasn’t there every day on HN, we'd wake up to an article from a new startup about how they split their app into 300 services so they could infinitely scale (never mind that they only had 100 MAUs today) so many companies never recovered from this it turns out, replacing simple function calls with network calls that could randomly fail isn't great for shipping velocity
1
298
do we get a another shrinkflation of the quota soon?
Polymarket
@PolymarketOct 20
JUST IN: Anthropic recorded a staggering $80,000,000,000.00 net loss in the first half of 2026.
390
Love my new Apple HomeView
1
2
321
iHome speaker charging stand, for sale at ~$50
28
being ai pilled is not the same as ai psychosis, i repeat
1
3
421
Roy Derks 🚀 retweeted
nader dabit
@dabit3Oct 19
I'd much rather work with someone who flexes much they accomplished with the fewest amount of tokens vs how many tokens they spent, and I sense this is a major trend in general How we quantify this as an industry is still TBD, probably a major new set of benchmarks
82
27
14
544
632,986
anyone remember using console.log() to debug instead of “claude pls fix”?
hannah
@erhannahOct 18
one day you wrote console.log("here") for the last time and didn't even know it
2
1
7
511
Reminder to spend every token in your quotas, in every tool or subscription you have These times won’t last
1
3
457
If your employer gives you tokens in whatever way, SPEND them
41
You don’t say
Polymarket
@PolymarketOct 17
JUST IN: Cybersecurity experts warn that AI agents are highly vulnerable to phishing emails containing hidden malicious instructions.
5
453
If an AI service is at capacity, let me leave the task in a queue. Show me that it’s waiting. Let me cancel it. Continue when there’s room. Clicking “try again” every few minutes is a strange job to give the human in an automation product.
2
6
479
The best harness knows how to get most out of both the data and the model Pure model agnostic harnesses will never get the most out of a model
1
443
2020: monorepos suck because developers can’t navigate them 2026: monorepos are awesome (because of AI)
4
14
1,223
Load more