Install
A constructive and inclusive social network for software developers. With you every step of your journey.
- 10,501articles · 30d
- 1+ hour agolatest article
- Aug 14, 2026earliest in window
- 97%with images
- 293avg words
- software 9,735
- coding 9,521
- development 9,489
- engineering 9,466
- community 9,448
- inclusive 9,409
- ai 7,987
- webdev 5,747
- programming 5,154
- productivity 3,502
- python 2,966
- technology 2,880
- artificial intelligence 2,827
- devops 2,732
- security 2,732
- llm 2,292
- architecture 2,259
- agents 2,160
- tutorial 2,104
- javascript 1,930
- Software Dev. 9,705
- Science & Technology 9,578
- Computers & Electronics 7,418
- Business & Industrial 812
- Internet & Telecom 771
- Economy, Business & Finance 383
- Finance 333
- Arts, Culture, Entertainment & Media 245
Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
Joint weight‑harness optimization approaches fine‑tuned model performance
5+ hour, 22+ min ago (634+ words) Alternating updates of model weights and executable harnesses can reach accuracy on par with full fine‑tuning while consuming a fraction of the training compute. The WHALE recipe shows that interleaving a short weight‑update phase with a lightweight harness…...
I Sell Memory APIs. I'm Also Building the Benchmark. Here's How I'm Trying Not to Rig It.
5+ hour, 18+ min ago (795+ words) Hey everyone. This time I'll go through what got me started on this benchmark, and the core of how it's actually built. All numbers below are from the current build. Nothing is final yet, so some of them will have…...
Context Window Management for Long-Running AI Agents: 4 Patterns That Work
5+ hour, 46+ min ago (650+ words) The agent had been running for four hours and it was arguing with itself about a file it had already fixed. For years I'd thought about context window management as a packing problem. How do I fit more in. That…...
AI Agent Memory: Sliding Windows, Summaries, and Vector Storage
6+ hour, 24+ min ago (623+ words) The agent we built in Post #4 has one big problem — the moment the script ends, it forgets everything. Next time you run it, it starts from zero. No memory of past conversations, no retained facts, nothing. For a quick experiment…...
When a Zero-Parameter Cache Overtakes a Transformer
7+ hour, 28+ min ago (574+ words) The question this series exists to answer, put in a form that can be measured: a transformer sees a fixed 64-token window, a count table over the current document sees the whole document, and as documents get longer, how much…...
The reply-length check existed for three weeks. The batch a human flagged never touched it: guarding the wrong path
8+ hour, 11+ min ago (339+ words) On 2026-09-05 the owner of our shop looked at three replies the agent was about to send and asked a... Tagged with ai, programming, devtools, claude....
I described 1,245 tables with an LLM and retrieval got worse
10+ hour, 51+ min ago (1126+ words) The cataloguing step is supposed to be the easy win. You have a schema whose tables are called ecm_template_link and v_pmpm, your users ask questions in English, and the gap between those two vocabularies is why retrieval misses. So you point a…...
How I pick a voice input setup for PC typing (2026)
12+ hour, 6+ min ago (304+ words) I type a lot on a laptop — chat replies, long AI prompts, the occasional email in another language — and the bottleneck is almost always the keyboard. Voice input helps, but “voice input” now means several different products that solve different…...
Oracle Integration Cloud Integration Patterns
11+ hour, 43+ min ago (162+ words) Twelve reusable patterns, real-world examples, and implementation guidance for Oracle Integration... Tagged with architecture, cloud, software....
The Model Wrote the Right Rule and My Replay Rejected It: The Extraction-vs-Replay Split
12+ hour, 24+ min ago (528+ words) CauterRule is an open-source sidecar that learns standing rules from repeated agent failures. It extracts lessons from trajectories, replay-tests them, and tries to separate reusable guidance from noisy overgeneralization. For two releases we treated "the pass rate is low" as…...