Jack Timonen (@Jack_Timonen) header
Jack Timonen (@Jack_Timonen) profile picture

Co-Founder of @GitHits_com | Code discovery infrastructure for software factories and agents, backed by a version-aware index

Joined June 2009
Photo by Jack Timonen (@Jack_Timonen)Photo by Jack Timonen (@Jack_Timonen)Photo by Jack Timonen (@Jack_Timonen)Photo by Jack Timonen (@Jack_Timonen)Photo by Jack Timonen (@Jack_Timonen)Photo by Jack Timonen (@Jack_Timonen)Photo by Jack Timonen (@Jack_Timonen)Photo by Jack Timonen (@Jack_Timonen)
Olli-Pekka Heinisuo wrote the Python package that flew to Mars on NASA's Ingenuity helicopter. Now he's building GitHits so coding agents can read open source the right way. @skvark of @GitHits_com on The Index with @afkehaya 🚁
4
1
10
1,119
Jack Timonen retweeted
A brief history of AI Coding since Nov 2025: Nov 2025: Opus 4.5 releases, OpenClaw gets built Dec 2025: community agrees that models get good enough to handle 95% of coding tasks Jan 2026: Ralph loops get popular, early efforts on loops/orchestration Feb: Everyone feels knackered, too much strategic decision-making, fears around cognitive debt begin Mar: Skills explosion as community converges around easy-to-share processes (superpowers already ahead of the game here) Apr: most SOTA devs haven't written a line of code in months May: "The unreasonable effectiveness of HTML" - more interest in richer review surfaces Jun: "Loop Engineering" wins vaguepost of the year, signals more hype around process Jul: Every talk in every conference becomes "here is my software factory" Aug: Opus 5 speaks incomprehensibly, interest in ASD-STE100 peaks Sep: Grok Bot gets popular, more interest in long-running "manager" threads which retain context and delegate work Oct: The promised speed gains haven't materialised, "dark factory" feels a long way off still Nov: No-slop manifesto releases, reading the code still appears essential TL;DR: no-one is writing code anymore, and we are still figuring out what that means
294
416
87
5,154
282,400
The difference @orca_build has made for our chief architect @jlitola has been huge! 2500 PRs in a month! Two other products that have made a difference: @bot, @avreacom githits.com/blog/how-i-build…
1
2
1
7
5,409
One mad developer. 2500 PRs in a month.
In August I was at 200+ PRs a week. In the last week of October I merged 707. I wrote up how my agent setup works now: who does what, how work flows from an idea to a merged PR, and what still needs me. githits.com/blog/how-i-build…
5
236
Somebody created a directory of emerging startups, the signals they leave behind, and the evidence worth following. startup-radar-grady.vercel.a…
3
55
If you care about licenses when developing... #ai #DevTools #LLMs
Qwen3 Coder Next left a license problem in 51 of 54 attempts. Gemini 4 Argon left one once. We ran 17 models through 22 coding scenarios without mentioning licenses. The blog breaks down which models and tasks failed most, and the one mistake nearly every model made.
2
76
Jack Timonen retweeted
Shikhu is in the GitHits index! Thanks for adding the GitHits badge to your repo @ArjunPatel777
2
2
8
149
Context matters, also in GTM
made 40 GTM brains with Pancake copy a brain and give that context to your agent gtmbrain.si our research on how context affects GTM recommendations below
2
66
Jack Timonen retweeted
Your agents can now pull the full OSV writeup on a vuln without leaving their terminal! New in the GitHits CLI and MCP: pkg vulns --details. Try it on [email protected] and you’ll get CVE-2026-4800
2
1
86
Jack Timonen retweeted
It's been a brutal few weeks for exploits. Your agent should be able to check a CVE before it ships code, not after. New in the GitHits CLI and MCP: give it a CVE or GHSA ID, get every affected package, the vulnerable ranges, and the fix. npx githits vulns CVE-2020-8203
2
3
177
Jack Timonen retweeted
I've been testing open models on computer use, and they get way better when they can also read the app's source. Qwen3.8-27B went from 24/60 to 44/60 on WebArena, mostly on rules the UI hides. Small test, our own tasks. Anyone else seen this?
1
3
123
Jack Timonen retweeted
I'm not building open source hoping to get acquired. I have friends already making $2M a year at OpenAI, $1.5M a year at SpaceX, and $4M a year at Meta. Joining an AI lab right now would probably make more financial sense for me. But I don’t want to. I just want to be my own boss and grind through my own product building journey. Call me stupid or naive or whatever 😆, but maybe I’m not alone here
430
88
29
3,228
149,028
Warning! Grok build can break the bank and cause you a massive bill - don't be as stupid as I was. I was using Grok build on my work laptop instead of my home computer and it turned out to be huge mistake. I thought it would use the remaining weekly credits on my SuperGrok Premium credits, but instead of it used API and it seems by default xAI API uses $20 up (I disabled the auto replenish credits, which should have never been made default). The total bill for 2 hours of coding was $111.41. I didn't notice it as I had sound turned off at my laptop and I got email for every $20, but only noticed it when it was too late. Those $111.41 bought me only ~110 million tokens with Grok 4.6 high. For comparison $1 would have bought me ~160 million tokens amount via DeepSeek (using Deepseek-flash max via official API). This makes Grok 4.6 approximately 160 times more expensive, which is a ridiculous price difference. Yes, you read it right. $10 of deepseek buys 1.6 billion tokens, $111 of Grok 4.6 use gives 110 million tokens. Deepseek-flash ~$0.00625 per 1M tokens Grok 4.6 ~$1 per 1M tokens These are real world usage numbers, same code base. Either Grok 4.6 runs on an extremely inefficient stack compared to Deepseek or their API profit margins are 99.98%. The estimate profit margin for Deepseek API are 80% or more. Note: most of the 2 hours of $111 "worth of coding" was just optimizing code and running relevant benchmarks (C++). There was very little prompting from my side. To make matters worse: despite having enough evidence and a solid plan Grok build failed to optimize my code enough. It is still far slower than CPython. $111 for a failure. Now I am delegating the task to Ainiux + deepseek combo.
9
4
2
35
2,810
Jack Timonen retweeted
GitHits now works on Googlesource repos and Dart packages. Point it at any go.googlesource.com repo. We asked Research when an oauth2 token counts as expired: 10 seconds before its actual expiry, cited to token.go. Dart works too. Grep on pub:[email protected] is pinned to the exact v1.2.2 tag. Live in the CLI and MCP 0.38.1.
3
3
5
179
Jack Timonen retweeted
A pattern for scaling cloud agents: Each agent only clones the repo it's changing into its sandbox. It reads its open source dependencies through GitHits, at the versions the lockfile pins. Right version in 192 of 192 runs. No snapshots. More in my write-up: githits.com/blog/sandbox-foo…
2
1
1
168
Jack Timonen retweeted
lodash 4.17.21 shipped with no release notes. It's also the release that fixed a command injection bug in _.template. GitHits now generates release notes from commits when none are published, and it flagged that fix as a security change. Run githits pkg changelog npm:[email protected] and see for yourself.
2
2
6
89
Jack Timonen retweeted
We have a couple ~3B models cooking, trained for prompt to GitHits query. DM me if you want early access 🚀
"You don't need a 5 trillion parameter model to write a JSON object." Nathan Burg (@NathanBurg) on where agent tokens go: writing queries. So @GitHits_com is building small specialized models just for that. The next event is on the calendar: lu.ma/oss4ai #AIAgents
2
4
204